chore: import upstream snapshot with attribution

.bazelrc

@@ -0,0 +1,272 @@
+common --noenable_bzlmod
+
+# Must be first. Enables build:windows, build:linux, build:macos, build:freebsd, build:openbsd
+build --enable_platform_specific_config
+
+build --incompatible_strict_action_env
+build:strict --incompatible_strict_action_env
+
+build:linux --workspace_status_command="bash ./bazel/workspace_status.sh"
+
+# To distinguish different incompatible environments.
+build --action_env=RAY_BUILD_ENV
+
+###############################################################################
+# On       Windows, provide: BAZEL_SH, and BAZEL_LLVM (if using clang-cl)
+# On all platforms, provide: PYTHON3_BIN_PATH=python
+###############################################################################
+build:windows --action_env=PATH
+# For --compilation_mode=dbg, consider enabling checks in the standard library as well (below).
+build --compilation_mode=opt
+# Using C++ 17 on all platforms.
+build:linux --host_cxxopt="-std=c++17"
+build:macos --host_cxxopt="-std=c++17"
+build:clang-cl --host_cxxopt="-std=c++17"
+build:msvc-cl --host_cxxopt="/std:c++17"
+build:windows --host_cxxopt="/std:c++17"
+build:linux --cxxopt="-std=c++17"
+build:macos --cxxopt="-std=c++17"
+build:clang-cl --cxxopt="-std=c++17"
+build:msvc-cl --cxxopt="/std:c++17"
+build:windows --cxxopt="/std:c++17"
+build:windows --cxxopt="/utf-8"
+# This workaround is needed to prevent Bazel from compiling the same file twice (once PIC and once not).
+build:linux --copt="-fPIC"
+build:macos --copt="-fPIC"
+build:clang-cl --compiler=clang-cl
+build:msvc-cl --compiler=msvc-cl
+# `LC_ALL` and `LANG` is needed for cpp worker tests, because they will call "ray start".
+# If we don't add them, python's `click` library will raise an error.
+test --test_env=LC_ALL
+test --test_env=LANG
+# Allow C++ worker tests to execute "ray start" with the correct version of Python.
+test --test_env=VIRTUAL_ENV
+test --test_env=PYENV_VIRTUAL_ENV
+test --test_env=PYENV_VERSION
+test --test_env=PYENV_SHELL
+# Do not send usage stats to the server for tests
+test --test_env=RAY_USAGE_STATS_REPORT_URL="http://127.0.0.1:8000"
+# Enable cluster mode for OSX and Windows. By default, Ray
+# will not allow multinode OSX and Windows clusters.
+test --test_env=RAY_ENABLE_WINDOWS_OR_OSX_CLUSTER="1"
+# Work around an NVIDIA driver bug that breaks NCCL cuMem host buffer
+# registration on non-P2P GPUs (e.g. T4) with CUDA error 217 (peer access not
+# supported), failing multi-GPU collectives. Affects drivers 560-575
+# (CUDA 12.6-12.9); NVIDIA fixed it in r580+ (see NVIDIA/nccl#1838).
+# TODO(elliot-barn): remove once the CI GPU fleet is on driver r580 or newer.
+test --test_env=NCCL_CUMEM_HOST_ENABLE=0
+# This is needed for some core tests to run correctly
+build:windows --enable_runfiles
+# TODO(mehrdadn): Revert the "-\\.(asm|S)$" exclusion when this Bazel bug
+#                 for compiling assembly files is fixed on Windows:
+#                 https://github.com/bazelbuild/bazel/issues/8924
+# Warnings should be errors
+build:linux    --per_file_copt="-\\.(asm|S)$@-Werror"
+build:macos    --per_file_copt="-\\.(asm|S)$@-Werror"
+build:clang-cl --per_file_copt="-\\.(asm|S)$@-Werror"
+build:msvc-cl     --per_file_copt="-\\.(asm|S)$@-WX"
+# Ignore warnings for protobuf generated files and external projects.
+build --per_file_copt="\\.pb\\.cc$@-w"
+build --per_file_copt="src/ray/thirdparty/.*$@-w"
+build:linux --per_file_copt="-\\.(asm|S)$,external/.*@-w,-Wno-error=implicit-function-declaration,-Wno-error=unused-function"
+build:macos --per_file_copt="-\\.(asm|S)$,external/.*@-w,-Wno-error=implicit-function-declaration,-Wno-error=unused-function,-Wno-missing-template-arg-list-after-template-kw"
+# Ignore warnings for host tools, which we generally can't control.
+# Ideally we only want to ignore warnings for external project
+# but the current bazel version doesn't support host_per_file_copt yet.
+build:macos --host_copt="-w"
+build:clang-cl --host_copt="-Wno-inconsistent-missing-override"
+build:clang-cl --host_copt="-Wno-microsoft-unqualified-friend"
+# This workaround is needed due to https://github.com/bazelbuild/bazel/issues/4341
+build --per_file_copt="-\\.(asm|S)$,external/com_github_grpc_grpc/.*@-DGRPC_BAZEL_BUILD"
+# Ignore wchar_t -> char conversion warning on MSVC
+build:msvc-cl --per_file_copt="external/boost/libs/regex/src/wc_regex_traits\\.cpp@-wd4244"
+build --http_timeout_scaling=5.0
+build --verbose_failures
+build:iwyu --aspects @com_github_storypku_bazel_iwyu//bazel/iwyu:iwyu.bzl%iwyu_aspect
+build:iwyu --output_groups=report
+
+# Print relative paths when possible
+build:windows --attempt_to_print_relative_paths
+# Save disk space by hardlinking cache hits instead of copying
+build:windows --experimental_repository_cache_hardlinks
+# For colored output (seems necessary on Windows)
+build:windows --color=yes
+# For compiler colored output (seems necessary on Windows)
+build:clang-cl --per_file_copt="-\\.(asm|S)$@-fansi-escape-codes"
+build:clang-cl --per_file_copt="-\\.(asm|S)$@-fcolor-diagnostics"
+
+# Debug build flags. Uncomment in '-c dbg' builds to enable checks in the C++ standard library:
+build:linux-debug --config linux
+build:linux-debug --cxxopt="-D_GLIBCXX_DEBUG=1"
+build:linux-debug --cxxopt="-D_GLIBCXX_DEBUG_PEDANTIC=1"
+build:linux-debug --cxxopt="-D_LIBCPP_DEBUG=1"
+build:macos-debug --config macos
+build:macos-debug --cxxopt="-D_GLIBCXX_DEBUG=1"
+build:macos-debug --cxxopt="-D_GLIBCXX_DEBUG_PEDANTIC=1"
+build:windows-debug --config windows
+build:windows-debug --cxxopt="-D_ITERATOR_DEBUG_LEVEL=2"
+
+# LLVM (clang & libc++) build flags common across Linux installations and systems.
+# On Ubuntu, the remaining configurations can be generated by running ci/env/install-llvm-binaries.sh
+build:llvm --action_env=CXXFLAGS=-stdlib=libc++
+build:llvm --action_env=LDFLAGS=-stdlib=libc++
+build:llvm --action_env=BAZEL_CXXOPTS=-stdlib=libc++
+build:llvm --action_env=BAZEL_LINKLIBS=-l%:libc++.a:-l%:libc++abi.a
+build:llvm --action_env=BAZEL_LINKOPTS=-lm:-pthread
+build:llvm --define force_libcpp=enabled
+
+# Thread sanitizer configuration:
+build:tsan --per_file_copt="-bazel-ray/external/com_github_antirez_redis/.*$@-fsanitize=thread"
+build:tsan --per_file_copt="-bazel-ray/external/com_github_antirez_redis/.*$@-DTHREAD_SANITIZER"
+build:tsan --strip=never
+build:tsan --copt -O2
+build:tsan --copt -g
+build:tsan --copt -fno-omit-frame-pointer
+build:tsan --copt -Wno-uninitialized
+build:tsan --linkopt -fsanitize=thread
+build:tsan --cxxopt="-D_RAY_TSAN_BUILD"
+build:tsan --no//:jemalloc_flag
+# This config is only for running TSAN with LLVM toolchain on Linux.
+build:tsan-clang --config=tsan
+build:tsan-clang --config=llvm
+test:tsan --test_env=TSAN_OPTIONS="report_atomic_races=0"
+
+# Memory sanitizer configuration
+build:asan --strip=never
+build:asan --copt -g
+build:asan --copt -fsanitize=address
+build:asan --copt -DADDRESS_SANITIZER
+build:asan --copt -fno-omit-frame-pointer
+build:asan --linkopt -fsanitize=address
+build:asan --no//:jemalloc_flag
+test:asan --jobs=1
+test:asan --test_env=ASAN_OPTIONS="detect_leaks=0"
+# This config is only for running ASAN with LLVM toolchain on Linux.
+# https://github.com/google/sanitizers/issues/1017
+build:asan-clang --config=asan
+build:asan-clang --config=llvm
+build:asan-clang --copt -mllvm
+build:asan-clang --copt -asan-use-private-alias=1
+
+build:asan-build --strip=never
+build:asan-build -c dbg
+build:asan-build --copt -fsanitize=address
+build:asan-build --copt -DADDRESS_SANITIZER
+build:asan-build --copt -O1
+build:asan-build --copt -g
+build:asan-build --copt -fno-omit-frame-pointer
+build:asan-build --copt -static-libasan
+build:asan-build --linkopt -fsanitize=address
+build:asan-build --linkopt -static-libasan
+# For example, for Ubuntu 18.04 libasan can be found here:
+# test:asan --test_env=LD_PRELOAD="/usr/lib/gcc/x86_64-linux-gnu/7/libasan.so"
+test:asan-buildkite --test_env=LD_PRELOAD="/usr/lib/x86_64-linux-gnu/libasan.so.5"
+
+# CI configuration:
+aquery:ci --color=no
+aquery:ci --noshow_progress
+
+test:ci-base --test_output=errors
+test:ci-base --test_verbose_timeout_warnings
+test:ci-base --flaky_test_attempts=2
+
+# Sending in PATH is required for tests to run on CI, after we enable
+# --incompatible_strict_action_env, until we either convert all Python tests to
+# hermetic tests -- which not only requires pinning all Python dependencies with bazel,
+# but also requires building ray(test) wheel with bazel. Alternatively, we can
+# also stop using bazel test to run ray's Python tests.
+#
+# This PATH test_env is intentionally not enabled on non-CI so that C/C++
+# tests, which are all hermetic, can build, test and cache as intended, ray
+# Python developers do not really use bazel test to run tests locally, but more
+# often just run tests with "pytest" directly.
+test:ci-base --test_env=PATH
+
+build:ci --color=yes
+build:ci --curses=no
+build:ci --keep_going
+build:ci --progress_report_interval=100
+build:ci --show_progress_rate_limit=15
+build:ci --ui_actions_shown=1024
+build:ci --show_timestamps
+# Retry on CacheNotFoundException from raw-S3 remote cache (AC/CAS eviction mismatch).
+# Remove once the cache is fronted by a server that coordinates AC/CAS eviction (bazel-remote, Buildbarn, etc.).
+build:ci --experimental_remote_cache_eviction_retries=3
+# Retry repository rule HTTP downloads (e.g. http_archive) on transient failures (502/504).
+build:ci --experimental_repository_downloader_retries=3
+# Disable test result caching because py_test under Bazel can import from outside of sandbox, but Bazel only looks at
+# declared dependencies to determine if a result should be cached. More details at:
+# https://github.com/bazelbuild/bazel/issues/7091, https://github.com/bazelbuild/rules_python/issues/382
+test:ci --config=ci-base
+test:ci --nocache_test_results
+test:ci --spawn_strategy=local
+test:ci --experimental_ui_max_stdouterr_bytes=-1
+
+test:ci-debug --config=ci-base
+test:ci-debug -c dbg
+test:ci-debug --copt="-g"
+# Disable test result caching for the same reason above.
+test:ci-debug --nocache_test_results
+test:ci-debug --spawn_strategy=local
+
+aquery:get-toolchain --include_commandline=false
+aquery:get-toolchain --noimplicit_deps
+
+# [Linux] Uncomment this line (or use --config) to print a stack trace on exit.
+#test:linux --config=strace
+test:strace --run_under="bash -c 'if command -v strace >/dev/null && strace -qq -k -e exit true 2>/dev/null; then strace -qq -k -e exit -e trace=\"!all\" -s 32768 -f -o >(awk \"/^[0-9]+ / { y = \\$3 != \\\"SIGCHLD\\\" && \\$3 != \\\"SIGTERM\\\" && \\$5 != \\\"SIGTERM\\\" && \\$5 != \\\"SIGKILL2\\\"; } y { print; }\" 1>&2 && cat 1>&2) -- \"$@\"; else \"$@\"; fi' -"
+# [Linux] Uncomment this line (or use --config) to preload libSegFault.so if available, to print a stack trace on aborts and segfault. (Note: This doesn't always work.)
+#test:linux --config=segfault
+test:segfault --run_under="bash -c 'unset GREP_OPTIONS && if ! grep -q -o Microsoft /proc/version 2>/dev/null; then libs=\"$(command -v ldconfig >/dev/null && ldconfig -p | grep -F -o -e \"libSegFault.so\" | uniq | tr \"\\\\n\" :)\" && if [ -n \"${libs%:}\" ]; then export SEGFAULT_SIGNALS=\"abrt segv\" LD_PRELOAD=\"${libs}${LD_PRELOAD-}\"; fi; fi && \"$@\"' -"
+
+# Debug build:
+build:debug -c dbg
+build:debug --copt="-g"
+build:debug --copt -fno-omit-frame-pointer
+build:debug --copt -fstack-protector-strong
+build:debug --copt -fcf-protection=full
+build:debug --strip="never"
+
+# Undefined Behavior Sanitizer
+build:ubsan --strip=never
+build:ubsan --copt -fno-sanitize=vptr
+build:ubsan --copt -fno-sanitize-recover=all
+build:ubsan --copt -g
+build:ubsan --linkopt -fsanitize=undefined
+build:ubsan --linkopt -fno-sanitize-recover=all
+build:ubsan --per_file_copt="-external/com_github_grpc_grpc/.*@-fsanitize=undefined"
+
+build:cgroup --sandbox_writable_path=/sys/fs/cgroup --config=llvm
+
+# Import local specific llvm config options, which can be generated by
+# ci/env/install-llvm-dependencies.sh
+try-import %workspace%/.llvm-local.bazelrc
+
+# Allow users to define custom options.
+try-import %workspace%/.user.bazelrc
+
+# Even with sandbox mode bazel prioritizes system headers over the ones in the sandbox.
+# It picks up the system headers when someone has protobuf installed via Homebrew.
+# Work around for https://github.com/bazelbuild/bazel/issues/8053
+build:macos --sandbox_block_path=/usr/local/
+build:macos --copt="-Wno-error=deprecated-declarations"
+# Disable build_bazel_apple_support's Apple CC toolchain on macOS CI machines
+# that only have Xcode CLT (no full Xcode.app). With BAZEL_NO_APPLE_CPP_TOOLCHAIN=1,
+# apple_cc_configure's _apple_cc_autoconf generates an empty local_config_apple_cc,
+# and Bazel falls back to the generic @local_config_cc (CLT clang), which worked
+# fine with Bazel 6.5. Without this, apple_cc_toolchain fails at analysis time with
+# "Xcode version must be specified to use an Apple CROSSTOOL" on CLT-only machines.
+build:macos --repo_env=BAZEL_NO_APPLE_CPP_TOOLCHAIN=1
+# The generic @local_config_cc CC toolchain (CLT-based, used when
+# BAZEL_NO_APPLE_CPP_TOOLCHAIN=1) defaults to -mmacosx-version-min=10.11 from
+# Bazel's built-in template. That's too old for std::filesystem (10.15+) and
+# std::visit/std::variant (10.13+) used by Ray and opentelemetry. Override to
+# 12.0 which matches the arm64 CI machines (Apple Silicon requires macOS 11+).
+build:macos --copt=-mmacosx-version-min=12.0
+build:macos --linkopt=-mmacosx-version-min=12.0
+# Host/exec-configuration builds (e.g. flatc, protoc built as tools) also need
+# the deployment target override; --host_copt applies to the exec configuration.
+build:macos --host_copt=-mmacosx-version-min=12.0
+build:macos --host_linkopt=-mmacosx-version-min=12.0
+# This option controls whether javac checks for missing direct dependencies.
+build --experimental_strict_java_deps=off

.bazelversion

@@ -0,0 +1 @@
+7.5.0

.buildkite/.sunset_civ1_linux

@@ -0,0 +1 @@
+2023-12-20

.buildkite/BUILD.bazel

@@ -0,0 +1,12 @@
+load("@py_deps_py310//:requirements.bzl", ci_require = "requirement")
+load("@rules_python//python:defs.bzl", "py_binary")
+
+py_binary(
+    name = "copy_files",
+    srcs = ["copy_files.py"],
+    visibility = ["//visibility:private"],
+    deps = [
+        ci_require("boto3"),
+        ci_require("aws_requests_auth"),
+    ],
+)

.buildkite/README.md

@@ -0,0 +1,18 @@
+# Buildkite pipelines
+
+This directory contains the Buildkite pipeline definitions for Ray CI, plus the rules that decide which tests run on a given change.
+
+## Pipelines
+
+Pipelines are defined in the `*.rayci.yml` files in this directory and are generated and run by [rayci](https://github.com/ray-project/rayci), Ray's CI orchestration tool. Each file groups the steps for one area (for example, `core.rayci.yml`, `data.rayci.yml`, `doc.rayci.yml`).
+
+## Conditional test selection
+
+Which steps run on a given pull request is determined by mapping changed file paths to *tags*. Two rule files drive this:
+
+- `test.rules.txt` is the conditional rule set. Rules are evaluated in order and the first match wins. A rule with no `@` tags is a skip rule (it matches but emits nothing), and a trailing `*` catch-all fans unmatched changes out to the full suite.
+- `always.rules.txt` is an always-on overlay applied to every change.
+
+rayci parses these files (its `test-rules` command) and runs the steps whose tags are emitted. See the header comment in each rules file for the full format.
+
+`ci/pipeline/determine_tests_to_run.py` is an in-repo reference implementation of the same rule-file format. It is not the live evaluator; rayci is.

.buildkite/_forge.rayci.yml

@@ -0,0 +1,11 @@
+group: forge
+sort_key: "_forge"
+steps:
+  - name: forge
+    wanda: ci/docker/forge.wanda.yaml
+
+  - name: manylinux-x86_64
+    wanda: ci/docker/manylinux.wanda.yaml
+    env_file: rayci.env
+    env:
+      HOSTTYPE: "x86_64"

.buildkite/_images.rayci.yml

@@ -0,0 +1,241 @@
+group: images
+sort_key: "_images"
+steps:
+  - name: raycpubase
+    label: "wanda: ray-py{{array.python}}-cpu-base"
+    tags:
+      - python_dependencies
+      - docker
+    wanda: docker/base-deps/cpu.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      ARCH_SUFFIX: ""
+
+  - name: raycpubaseextra
+    label: "wanda: ray-py{{array.python}}-cpu-base-extra"
+    wanda: docker/base-extra/cpu.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      IMAGE_TYPE: "ray"
+      ARCH_SUFFIX: ""
+    depends_on: raycpubase($)
+
+  - name: raytpubase
+    label: "wanda: ray-py{{array.python}}-tpu-base"
+    tags:
+      - python_dependencies
+      - docker
+    wanda: docker/base-deps/tpu.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      ARCH_SUFFIX: ""
+
+  - name: raycudabase
+    label: "wanda: ray-py{{array.python}}-cu{{array.cuda}}-base"
+    tags:
+      - python_dependencies
+      - docker
+    wanda: docker/base-deps/cuda.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+      cuda:
+        - "11.7.1-cudnn8"
+        - "11.8.0-cudnn8"
+        - "12.1.1-cudnn8"
+        - "12.3.2-cudnn9"
+        - "12.4.1-cudnn"
+        - "12.5.1-cudnn"
+        - "12.6.3-cudnn"
+        - "12.8.1-cudnn"
+        - "12.9.1-cudnn"
+        - "13.0.0-cudnn"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      CUDA_VERSION: "{{array.cuda}}"
+      ARCH_SUFFIX: ""
+
+  - name: raycudabaseextra
+    label: "wanda: ray-py{{array.python}}-cu{{array.cuda}}-base-extra"
+    wanda: docker/base-extra/cuda.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+      cuda:
+        - "11.7.1-cudnn8"
+        - "11.8.0-cudnn8"
+        - "12.1.1-cudnn8"
+        - "12.3.2-cudnn9"
+        - "12.4.1-cudnn"
+        - "12.5.1-cudnn"
+        - "12.6.3-cudnn"
+        - "12.8.1-cudnn"
+        - "12.9.1-cudnn"
+        - "13.0.0-cudnn"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      CUDA_VERSION: "{{array.cuda}}"
+      IMAGE_TYPE: "ray"
+      ARCH_SUFFIX: ""
+    depends_on: raycudabase($)
+
+  - name: ray-llmbase
+    label: "wanda: ray-llm-py{{array.python}}-cu{{array.cuda}}-base"
+    tags:
+      - python_dependencies
+      - docker
+    wanda: docker/ray-llm/cuda.wanda.yaml
+    depends_on: raycudabase($)
+    array:
+      python:
+        - "3.12"
+      cuda:
+        - "13.0.0-cudnn"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      CUDA_VERSION: "{{array.cuda}}"
+
+  - name: ray-llmbaseextra
+    label: "wanda: ray-llm-py{{array.python}}-cu{{array.cuda}}-base-extra"
+    wanda: docker/base-extra/cuda.wanda.yaml
+    array:
+      python:
+        - "3.12"
+      cuda:
+        - "13.0.0-cudnn"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      CUDA_VERSION: "{{array.cuda}}"
+      IMAGE_TYPE: "ray-llm"
+      ARCH_SUFFIX: ""
+    depends_on: ray-llmbase($)
+
+  - name: ray-mlcpubase
+    label: "wanda: ray-ml-py{{array.python}}-cpu-base"
+    tags:
+      - python_dependencies
+      - docker
+    wanda: docker/ray-ml/cpu.wanda.yaml
+    depends_on: raycpubase($)
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+
+  - name: ray-mlcpubaseextra
+    label: "wanda: ray-ml-py{{array.python}}-cpu-base-extra"
+    wanda: docker/base-extra/cpu.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      IMAGE_TYPE: "ray-ml"
+      ARCH_SUFFIX: ""
+    depends_on: ray-mlcpubase($)
+
+  - name: ray-mlcudabase
+    label: "wanda: ray-ml-py{{array.python}}-cu{{array.cuda}}-base"
+    tags:
+      - python_dependencies
+      - docker
+    wanda: docker/ray-ml/cuda.wanda.yaml
+    depends_on: raycudabase($)
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+      cuda:
+        - "12.1.1-cudnn8"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      CUDA_VERSION: "{{array.cuda}}"
+
+  - name: ray-mlcudabaseextra
+    label: "wanda: ray-ml-py{{array.python}}-cu{{array.cuda}}-base-extra"
+    wanda: docker/base-extra/cuda.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+      cuda:
+        - "12.1.1-cudnn8"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      CUDA_VERSION: "{{array.cuda}}"
+      IMAGE_TYPE: "ray-ml"
+      ARCH_SUFFIX: ""
+    depends_on: ray-mlcudabase($)
+
+  - name: ray-slimcpubase
+    label: "wanda: ray-slim-py{{array.python}}-cpu-base"
+    tags:
+      - python_dependencies
+      - docker
+      - skip-on-release-tests
+    wanda: docker/base-slim/cpu.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      ARCH_SUFFIX: ""
+
+  - name: ray-slimcudabase
+    label: "wanda: ray-slim-py{{array.python}}-cu{{array.cuda}}-base"
+    tags:
+      - python_dependencies
+      - docker
+      - skip-on-release-tests
+    wanda: docker/base-slim/cuda.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+      cuda:
+        - "11.7.1"
+        - "11.8.0"
+        - "12.1.1"
+        - "12.3.2"
+        - "12.4.1"
+        - "12.5.1"
+        - "12.6.3"
+        - "12.8.1"
+        - "12.9.1"
+        - "13.0.0"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      CUDA_VERSION: "{{array.cuda}}"
+      ARCH_SUFFIX: ""

.buildkite/_wheel-build.rayci.yml

@@ -0,0 +1,84 @@
+group: wheel build
+sort_key: "_wheel-build"
+steps:
+  - name: ray-core-build
+    label: "wanda: core binary parts py{{array.python}} (x86_64)"
+    wanda: ci/docker/ray-core.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+        - "3.14"
+    env_file: rayci.env
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      ARCH_SUFFIX: ""
+      HOSTTYPE: "x86_64"
+    tags:
+      - release_wheels
+
+  - name: ray-dashboard-build
+    label: "wanda: dashboard (x86_64)"
+    wanda: ci/docker/ray-dashboard.wanda.yaml
+    env_file: rayci.env
+    env:
+      ARCH_SUFFIX: ""
+      HOSTTYPE: "x86_64"
+    tags:
+      - release_wheels
+
+  - name: ray-java-build
+    label: "wanda: java build (x86_64)"
+    wanda: ci/docker/ray-java.wanda.yaml
+    env_file: rayci.env
+    env:
+      ARCH_SUFFIX: ""
+      HOSTTYPE: "x86_64"
+    tags:
+      - release_wheels
+      - java
+
+  - name: ray-wheel-build
+    label: "wanda: wheel py{{array.python}} (x86_64)"
+    wanda: ci/docker/ray-wheel.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+        - "3.14"
+    env_file: rayci.env
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      ARCH_SUFFIX: ""
+      HOSTTYPE: "x86_64"
+      JDK_SUFFIX: "-jdk"
+      RAY_JAVA_IMAGE: "cr.ray.io/rayproject/ray-java-build"
+      RAY_DASHBOARD_IMAGE: "cr.ray.io/rayproject/ray-dashboard"
+    tags:
+      - release_wheels
+      - linux_wheels
+    depends_on:
+      - ray-core-build($)
+      - ray-java-build
+      - ray-dashboard-build
+
+  - name: ray-wheel-minimal-build
+    label: "wanda: wheel-minimal py3.13 (x86_64)"
+    wanda: ci/docker/ray-wheel.wanda.yaml
+    env_file: rayci.env
+    env:
+      PYTHON_VERSION: "3.13"
+      ARCH_SUFFIX: ""
+      HOSTTYPE: "x86_64"
+      JDK_SUFFIX: ""
+      RAY_JAVA_IMAGE: "scratch"
+      RAY_DASHBOARD_IMAGE: "scratch"
+    tags:
+      - release_wheels
+      - linux_wheels
+    depends_on:
+      - ray-core-build(python=3.13)

.buildkite/always.rules.test.txt

@@ -0,0 +1,10 @@
+# Unit tests for always.rules.txt
+#
+# Format: file_path: tag1 tag2 tag3
+#
+# This rules file adds "always lint" to all files via wildcard fallthrough.
+
+# Any file gets always lint tags
+some/random/file.txt: always lint
+python/ray/actor.py: always lint
+doc/source/index.rst: always lint

.buildkite/always.rules.txt

@@ -0,0 +1,20 @@
+# Ray CI conditional testing rules definition files. Applied to all files.
+#
+# Comment content, after '#', will be ignored.
+# Empty lines will be ignored too.
+#
+#   ! tag1 tag2 tag3  # Declares a tag. A tag must be declared first to be used.
+#   # Tags must be declared at the beginning.
+#
+#   dir/  # Directory to match
+#   file  # File to match
+#   dir/*.py  # Pattern to match, using fnmatch, matches dir/a.py dir/dir/b.py or dir/.py
+#   @ tag1 tag2 tag3  # Tags to emit for a rule. A rule without tags is a skipping rule.
+#
+#   ;  # Semicolon to separate rules
+
+! always lint
+
+*
+@ always lint
+;

.buildkite/base.rayci.yml

@@ -0,0 +1,78 @@
+group: base
+steps:
+  - name: oss-ci-base_test-multipy
+    label: "wanda: oss-ci-base_test-py{{array.python}}"
+    wanda: ci/docker/base.test.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+        - "3.14"
+    env:
+      PYTHON: "{{array.python}}"
+
+  - name: oss-ci-base_build-multipy
+    label: "wanda: oss-ci-base_build-py{{array.python}}"
+    wanda: ci/docker/base.build.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+    env:
+      PYTHON: "{{array.python}}"
+    depends_on: oss-ci-base_test-multipy($)
+    tags: cibase
+
+  - name: oss-ci-base_test-aarch64
+    wanda: ci/docker/base.test.aarch64.wanda.yaml
+    instance_type: builder-arm64
+
+  - name: oss-ci-base_build-aarch64
+    wanda: ci/docker/base.build.aarch64.wanda.yaml
+    depends_on: oss-ci-base_test-aarch64
+    env:
+      PYTHON: "3.10"
+    instance_type: builder-arm64
+
+  - name: oss-ci-base_ml-multipy
+    label: "wanda: oss-ci-base_ml-py{{array.python}}"
+    wanda: ci/docker/base.ml.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+    env:
+      PYTHON: "{{array.python}}"
+    depends_on: oss-ci-base_test-multipy($)
+
+  - name: oss-ci-base_gpu-multipy
+    label: "wanda: oss-ci-base_gpu-py{{array.python}}"
+    wanda: ci/docker/base.gpu.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+    env:
+      PYTHON: "{{array.python}}"
+    tags: cibase
+
+  - name: oss-ci-base_cu128-multipy
+    label: "wanda: oss-ci-base_cu128-py3.11"
+    wanda: ci/docker/base.cu128.wanda.yaml
+    env:
+      PYTHON: "3.11"
+
+  - name: oss-ci-base_cu130-multipy
+    label: "wanda: oss-ci-base_cu130-py{{array.python}}"
+    wanda: ci/docker/base.cu130.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.12"
+    env:
+      PYTHON: "{{array.python}}"

.buildkite/bisect/_forge.rayci.yml

@@ -0,0 +1,4 @@
+group: forge
+steps:
+  - name: forge
+    wanda: ci/docker/forge.wanda.yaml

.buildkite/bisect/bisect.rayci.yml

@@ -0,0 +1,23 @@
+group: bisect
+depends_on:
+  - forge
+steps:
+  - name: macos test
+    if: build.env("RAYCI_TEST_TYPE") != null && build.env("RAYCI_TEST_TYPE") == "macos_test"
+    commands:
+      - if [[ "$(buildkite-agent meta-data get test-type)" != "macos_test" ]]; then exit 0; fi
+      - RAYCI_BISECT_RUN=1 ./ci/ray_ci/macos/macos_ci.sh bisect "$(buildkite-agent meta-data get test-name)"
+          "$(buildkite-agent meta-data get passing-commit)" "$(buildkite-agent meta-data get failing-commit)"
+    mount_buildkite_agent: true
+    job_env: MACOS
+    instance_type: macos-arm64
+    priority: 10
+
+  - name: linux or windows test
+    if: build.env("RAYCI_TEST_TYPE") != null && (build.env("RAYCI_TEST_TYPE") == "linux_test" || build.env("RAYCI_TEST_TYPE") == "windows_test")
+    commands:
+      - if [[ "$(buildkite-agent meta-data get test-type)" != "linux_test" && "$(buildkite-agent meta-data get test-type)" != "windows_test" ]]; then exit 0; fi
+      - bazel run //ci/ray_ci/bisect:bisect_test "$(buildkite-agent meta-data get test-name)"
+          "$(buildkite-agent meta-data get passing-commit)" "$(buildkite-agent meta-data get failing-commit)"
+    mount_buildkite_agent: true
+    priority: 10

.buildkite/bisect/config.yml

@@ -0,0 +1,21 @@
+name: ray-bisect
+artifacts_bucket: ray-ci-artifact-branch-public
+ci_temp: s3://ray-ci-artifact-branch-public/ci-temp/
+ci_work_repo: 029272617770.dkr.ecr.us-west-2.amazonaws.com/rayproject/citemp
+forge_prefix: cr.ray.io/rayproject/
+builder_queues:
+  builder: builder_queue_branch
+runner_queues:
+  default: runner_queue_small_branch
+  macos-arm64: macos-branch-arm64
+buildkite_dirs:
+  - .buildkite/bisect
+build_env_keys:
+  - RAYCI_TEST_TYPE
+env:
+  BUILDKITE_BAZEL_CACHE_URL: https://bazel-cache-dev.s3.us-west-2.amazonaws.com
+  RAYCI_SKIP_UPLOAD: "true"
+hook_env_keys:
+  - RAYCI_CHECKOUT_DIR
+docker_plugin:
+  allow_mount_buildkite_agent: true

.buildkite/build.rayci.yml

@@ -0,0 +1,437 @@
+group: build
+steps:
+  - label: ":arrow_up: upload: wheel py{{array.python}} (x86_64)"
+    key: linux_wheels_upload
+    instance_type: small
+    commands:
+      - bazel run //ci/ray_ci/automation:extract_wanda_artifact --
+        --wanda-image-name=ray-wheel-py{{array.python}}
+        --file-glob='*.whl'
+        --output-dir=.whl
+      - ./ci/build/copy_build_artifacts.sh wheel
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+        - "3.14"
+    depends_on:
+      - ray-wheel-build($)
+      - forge
+    tags:
+      - release_wheels
+      - linux_wheels
+      - oss
+      - skip-on-premerge
+
+  - name: ray-cpp-core-build
+    label: "wanda: cpp core (x86_64)"
+    wanda: ci/docker/ray-cpp-core.wanda.yaml
+    env_file: rayci.env
+    env:
+      ARCH_SUFFIX: ""
+      HOSTTYPE: "x86_64"
+    tags:
+      - release_wheels
+      - oss
+
+  - name: ray-cpp-wheel-build
+    label: "wanda: cpp wheel (x86_64)"
+    wanda: ci/docker/ray-cpp-wheel.wanda.yaml
+    env_file: rayci.env
+    env:
+      PYTHON_VERSION: "3.10"  # Used for upstream images; wheel is Python-agnostic
+      ARCH_SUFFIX: ""
+      HOSTTYPE: "x86_64"
+    tags:
+      - release_wheels
+      - linux_wheels
+      - oss
+    depends_on:
+      - ray-core-build(python=3.10)
+      - ray-cpp-core-build
+      - ray-java-build
+      - ray-dashboard-build
+
+  - label: ":arrow_up: upload: cpp wheel (x86_64)"
+    key: linux_cpp_wheels_upload
+    instance_type: small
+    commands:
+      - bazel run //ci/ray_ci/automation:extract_wanda_artifact --
+        --wanda-image-name=ray-cpp-wheel
+        --file-glob='*.whl'
+        --output-dir=.whl
+      - ./ci/build/copy_build_artifacts.sh wheel
+    depends_on:
+      - ray-cpp-wheel-build
+      - forge
+    tags:
+      - release_wheels
+      - linux_wheels
+      - oss
+      - skip-on-premerge
+
+  - label: ":tapioca: build: jar"
+    key: java_wheels
+    tags:
+      - java
+      - oss
+    instance_type: medium
+    commands:
+      - ./ci/build/build-manylinux-ray.sh
+      - ./ci/build/build-manylinux-jar.sh
+      - ./ci/build/copy_build_artifacts.sh jar
+    depends_on: manylinux-x86_64
+    job_env: manylinux-x86_64
+
+  - name: ray-image-cpu-build
+    label: "wanda: ray py{{array.python}} cpu (x86_64)"
+    wanda: ci/docker/ray-image-cpu.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+    env_file: rayci.env
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      ARCH_SUFFIX: ""
+    tags:
+      - python_dependencies
+      - docker
+      - oss
+    depends_on:
+      - ray-wheel-build($)
+      - raycpubase($)
+
+  - name: ray-image-tpu-build
+    label: "wanda: ray py{{array.python}} tpu (x86_64)"
+    wanda: ci/docker/ray-image-tpu.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+    env_file: rayci.env
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      ARCH_SUFFIX: ""
+    tags:
+      - python_dependencies
+      - docker
+      - oss
+    depends_on:
+      - ray-wheel-build($)
+      - raytpubase($)
+
+  - label: ":tapioca: smoke test: ray tpu image"
+    instance_type: small
+    tags:
+      - python_dependencies
+      - docker
+      - oss
+    commands:
+      - aws ecr get-login-password --region us-west-2 | docker login --username AWS --password-stdin 029272617770.dkr.ecr.us-west-2.amazonaws.com
+      - docker run --rm
+        "$${RAYCI_WORK_REPO}":"$${RAYCI_BUILD_ID}"-ray-py3.10-tpu
+        /bin/bash -c "python -c \"import ray; print('ray', ray.__version__); import jax; print('jax', jax.__version__)\""
+    depends_on:
+      - ray-image-tpu-build(python=3.10)
+      - forge
+
+  - name: ray-image-cuda-build
+    label: "wanda: ray py{{array.python}} cu{{array.cuda}} (x86_64)"
+    wanda: ci/docker/ray-image-cuda.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+      cuda:
+        - "11.7.1-cudnn8"
+        - "11.8.0-cudnn8"
+        - "12.1.1-cudnn8"
+        - "12.3.2-cudnn9"
+        - "12.4.1-cudnn"
+        - "12.5.1-cudnn"
+        - "12.6.3-cudnn"
+        - "12.8.1-cudnn"
+        - "12.9.1-cudnn"
+        - "13.0.0-cudnn"
+    env_file: rayci.env
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      CUDA_VERSION: "{{array.cuda}}"
+      ARCH_SUFFIX: ""
+    tags:
+      - python_dependencies
+      - docker
+      - oss
+    depends_on:
+      - ray-wheel-build($)
+      - raycudabase($)
+
+  - label: ":crane: publish: ray py{{array.python}} (x86_64)"
+    key: ray_images_push
+    instance_type: small
+    commands:
+      - bazel run //.buildkite:copy_files -- --destination docker_login
+      - bazel run //ci/ray_ci/automation:push_ray_image --
+        --python-version {{array.python}}
+        --platform cpu
+        --platform tpu
+        --platform cu11.7.1-cudnn8
+        --platform cu11.8.0-cudnn8
+        --platform cu12.1.1-cudnn8
+        --platform cu12.3.2-cudnn9
+        --platform cu12.4.1-cudnn
+        --platform cu12.5.1-cudnn
+        --platform cu12.6.3-cudnn
+        --platform cu12.8.1-cudnn
+        --platform cu12.9.1-cudnn
+        --platform cu13.0.0-cudnn
+        --image-type ray
+        --architecture x86_64
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+    depends_on:
+      - ray-image-cpu-build($)
+      - ray-image-tpu-build($)
+      - ray-image-cuda-build($)
+    tags:
+      - python_dependencies
+      - docker
+      - oss
+      - skip-on-premerge
+
+  - name: ray-extra-image-cpu-build
+    label: "wanda: ray-extra py{{array.python}} cpu (x86_64)"
+    wanda: ci/docker/ray-extra-image-cpu.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+    env_file: rayci.env
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      ARCH_SUFFIX: ""
+    tags:
+      - python_dependencies
+      - docker
+      - oss
+    depends_on:
+      - ray-wheel-build($)
+      - raycpubaseextra($)
+
+  - name: ray-extra-image-cuda-build
+    label: "wanda: ray-extra py{{array.python}} cu{{array.cuda}} (x86_64)"
+    wanda: ci/docker/ray-extra-image-cuda.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+      cuda:
+        - "11.7.1-cudnn8"
+        - "11.8.0-cudnn8"
+        - "12.1.1-cudnn8"
+        - "12.3.2-cudnn9"
+        - "12.4.1-cudnn"
+        - "12.5.1-cudnn"
+        - "12.6.3-cudnn"
+        - "12.8.1-cudnn"
+        - "12.9.1-cudnn"
+        - "13.0.0-cudnn"
+    env_file: rayci.env
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      CUDA_VERSION: "{{array.cuda}}"
+      ARCH_SUFFIX: ""
+    tags:
+      - python_dependencies
+      - docker
+      - oss
+    depends_on:
+      - ray-wheel-build($)
+      - raycudabaseextra($)
+
+  - name: ray-llm-image-cuda-build
+    label: "wanda: ray-llm py{{array.python}} cu{{array.cuda}} (x86_64)"
+    wanda: ci/docker/ray-llm-image-cuda.wanda.yaml
+    array:
+      python:
+        - "3.12"
+      cuda:
+        - "13.0.0-cudnn"
+    env_file: rayci.env
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      CUDA_VERSION: "{{array.cuda}}"
+      ARCH_SUFFIX: ""
+    tags:
+      - python_dependencies
+      - docker
+      - oss
+    depends_on:
+      - ray-wheel-build($)
+      - ray-llmbase($)
+
+  - name: ray-llm-extra-image-cuda-build
+    label: "wanda: ray-llm-extra py{{array.python}} cu{{array.cuda}} (x86_64)"
+    wanda: ci/docker/ray-llm-extra-image-cuda.wanda.yaml
+    array:
+      python:
+        - "3.12"
+      cuda:
+        - "13.0.0-cudnn"
+    env_file: rayci.env
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      CUDA_VERSION: "{{array.cuda}}"
+      ARCH_SUFFIX: ""
+    tags:
+      - python_dependencies
+      - docker
+      - oss
+    depends_on:
+      - ray-wheel-build($)
+      - ray-llmbaseextra($)
+
+  - label: ":crane: publish: ray-extra py{{array.python}} (x86_64)"
+    key: ray_extra_images_push
+    instance_type: small
+    commands:
+      - bazel run //.buildkite:copy_files -- --destination docker_login
+      - bazel run //ci/ray_ci/automation:push_ray_image --
+        --python-version {{array.python}}
+        --platform cpu
+        --platform cu11.7.1-cudnn8
+        --platform cu11.8.0-cudnn8
+        --platform cu12.1.1-cudnn8
+        --platform cu12.3.2-cudnn9
+        --platform cu12.4.1-cudnn
+        --platform cu12.5.1-cudnn
+        --platform cu12.6.3-cudnn
+        --platform cu12.8.1-cudnn
+        --platform cu12.9.1-cudnn
+        --platform cu13.0.0-cudnn
+        --image-type ray-extra
+        --architecture x86_64
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+    depends_on:
+      - ray-extra-image-cpu-build($)
+      - ray-extra-image-cuda-build($)
+    tags:
+      - python_dependencies
+      - docker
+      - oss
+      - skip-on-premerge
+
+  - label: ":crane: publish: ray-llm py{{array.python}} {{array.platform}} (x86_64)"
+    key: ray_llm_images_cuda_push
+    instance_type: small
+    commands:
+      - bazel run //.buildkite:copy_files -- --destination docker_login
+      - bazel run //ci/ray_ci/automation:push_ray_image --
+        --python-version {{array.python}}
+        --platform {{array.platform}}
+        --image-type ray-llm
+        --architecture x86_64
+    array:
+      python:
+        - "3.12"
+      platform:
+        - cu13.0.0-cudnn
+    depends_on:
+      - ray-llm-image-cuda-build($)
+    tags:
+      - python_dependencies
+      - docker
+      - oss
+      - skip-on-premerge
+
+  - label: ":crane: publish: ray-llm-extra py{{array.python}} {{array.platform}} (x86_64)"
+    key: ray_llm_extra_images_cuda_push
+    instance_type: small
+    commands:
+      - bazel run //.buildkite:copy_files -- --destination docker_login
+      - bazel run //ci/ray_ci/automation:push_ray_image --
+        --python-version {{array.python}}
+        --platform {{array.platform}}
+        --image-type ray-llm-extra
+        --architecture x86_64
+    array:
+      python:
+        - "3.12"
+      platform:
+        - cu13.0.0-cudnn
+    depends_on:
+      - ray-llm-extra-image-cuda-build($)
+    tags:
+      - python_dependencies
+      - docker
+      - oss
+      - skip-on-premerge
+
+  - label: ":tapioca: smoke test build-wheel.sh --help"
+    tags:
+      - tools
+    instance_type: small
+    commands:
+      - ./build-wheel.sh --help
+    depends_on:
+      - forge
+
+  - label: ":tapioca: smoke test build-docker.sh"
+    tags:
+      - python_dependencies
+      - docker
+      - oss
+    instance_type: medium
+    soft_fail: true
+    commands:
+      - export WHEEL_URL="https://files.pythonhosted.org/packages/93/f1/9108c4f878e3cacb767b7dfbbc3a26537c79ab516d2530b9f63b558ba4bb/ray-2.44.1-cp310-cp310-manylinux2014_x86_64.whl"
+      - export CPP_WHEEL_URL="https://files.pythonhosted.org/packages/d3/cf/ef6d5a9a688001f73e4749c48f840455ecec11acde982eb70f387b0dc445/ray_cpp-2.44.1-cp310-cp310-manylinux2014_x86_64.whl"
+      - bash build-docker.sh --progress-plain
+      - docker run -ti --rm rayproject/ray:dev python -c "import ray; print(ray.__version__)"
+    depends_on:
+      - forge
+
+  - label: ":tapioca: smoke test build-image.sh --help"
+    tags:
+      - tools
+    instance_type: small
+    commands:
+      - ./build-image.sh --help
+    depends_on:
+      - forge
+
+  - label: ":tapioca: generate nightly indexes"
+    instance_type: small
+    tags:
+      - docker
+      - oss
+      - skip-on-premerge
+    commands:
+      - bazel run .buildkite:copy_files -- --destination docker_login
+      - bazel run //ci/ray_ci/automation:generate_index -- --prefix nightly
+    depends_on:
+      - ray_images_push(*)
+      - ray_images_push_aarch64(*)
+      - forge

.buildkite/cicd-cron/_forge.rayci.yml

@@ -0,0 +1,6 @@
+group: forge
+sort_key: "_forge"
+steps:
+  - name: forge
+    instance_type: builder-x86_64
+    wanda: ci/docker/forge.wanda.yaml

.buildkite/cicd-cron/cicd-cron.rayci.yml

@@ -0,0 +1,70 @@
+group: cicd-cron
+steps:
+  # NOTE(andrew-anyscale): 'name' is used for both naming the wanda image, as
+  # well as for generating step names. Step name cannot contain a {{}} placeholder,
+  # so we cannot use a matrix here.
+  # See: https://github.com/ray-project/rayci/blob/74cdca5848d8ff0c9dcad464d74fc2e5cd61fa13/raycicmd/wanda.go#L53
+  - name: manylinux-cibase-x86_64
+    label: ":magic_wand: wanda: manylinux-cibase-x86_64"
+    wanda: ci/docker/manylinux-cibase.wanda.yaml
+    instance_type: builder-x86_64
+    env:
+      RAYCI_DISABLE_JAVA: "true"
+      RAYCI_WANDA_ALWAYS_REBUILD: "true"
+      JDK_SUFFIX: ""
+      HOSTTYPE: "x86_64"
+
+  - name: manylinux-cibase-aarch64
+    label: ":magic_wand: wanda: manylinux-cibase-aarch64"
+    wanda: ci/docker/manylinux-cibase.wanda.yaml
+    instance_type: builder-aarch64
+    env:
+      RAYCI_DISABLE_JAVA: "true"
+      RAYCI_WANDA_ALWAYS_REBUILD: "true"
+      JDK_SUFFIX: ""
+      HOSTTYPE: "aarch64"
+
+  - name: manylinux-cibase-jdk-x86_64
+    label: ":magic_wand: wanda: manylinux-cibase-jdk-x86_64"
+    wanda: ci/docker/manylinux-cibase.wanda.yaml
+    instance_type: builder-x86_64
+    env:
+      RAYCI_DISABLE_JAVA: "false"
+      RAYCI_WANDA_ALWAYS_REBUILD: "true"
+      JDK_SUFFIX: "-jdk"
+      HOSTTYPE: "x86_64"
+
+  - name: manylinux-cibase-jdk-aarch64
+    label: ":magic_wand: wanda: manylinux-cibase-jdk-aarch64"
+    wanda: ci/docker/manylinux-cibase.wanda.yaml
+    instance_type: builder-aarch64
+    env:
+      RAYCI_DISABLE_JAVA: "false"
+      RAYCI_WANDA_ALWAYS_REBUILD: "true"
+      JDK_SUFFIX: "-jdk"
+      ARCH_SUFFIX: "aarch64"
+      HOSTTYPE: "aarch64"
+
+  - label: ":docker: push: Push manylinux-cibase{{matrix.jdk_suffix}}{{matrix.host_suffix}} to Docker Hub"
+    depends_on:
+      - manylinux-cibase-x86_64
+      - manylinux-cibase-aarch64
+      - manylinux-cibase-jdk-x86_64
+      - manylinux-cibase-jdk-aarch64
+      - forge
+    job_env: forge
+    matrix:
+      setup:
+        host_suffix:
+          - "-x86_64"
+          - "-aarch64"
+        jdk_suffix:
+          - ""
+          - "-jdk"
+    commands:
+      - bazel run //.buildkite:copy_files -- --destination docker_login
+      - bazel run //ci/ray_ci/automation:copy_wanda_image --
+        --wanda-image-name manylinux-cibase{{matrix.jdk_suffix}}{{matrix.host_suffix}}
+        --destination-repository rayproject/manylinux2014
+        --tag-suffix {{matrix.jdk_suffix}}{{matrix.host_suffix}}
+        --upload

.buildkite/cicd-cron/config.yaml

@@ -0,0 +1,18 @@
+name: ray-cicd-cron
+artifacts_bucket: ray-ci-artifact-branch-public
+ci_temp: s3://ray-ci-artifact-branch-public/ci-temp/
+ci_work_repo: 029272617770.dkr.ecr.us-west-2.amazonaws.com/rayproject/citemp
+forge_prefix: cr.ray.io/rayproject/
+builder_queues:
+  builder-x86_64: builder_queue_branch
+  builder-aarch64: builder_queue_arm64_branch
+runner_queues:
+  default: runner_queue_small_branch
+buildkite_dirs:
+  - .buildkite/cicd-cron
+env:
+  BUILDKITE_BAZEL_CACHE_URL: https://bazel-cache-dev.s3.us-west-2.amazonaws.com
+hook_env_keys:
+  - RAYCI_CHECKOUT_DIR
+docker_plugin:
+  allow_mount_buildkite_agent: true

.buildkite/cicd.rayci.yml

@@ -0,0 +1,51 @@
+group: reef tests
+depends_on:
+  - forge
+steps:
+  - label: ":test_tube: test-rules"
+    key: test-rules
+    commands:
+      - curl -sfL "https://raw.githubusercontent.com/ray-project/rayci/stable/run_rayci.sh" | bash -s -- test-rules
+    instance_type: small
+    tags:
+      - tools
+      - always
+  - label: ":coral: reef: ci+release tooling tests"
+    key: reef-tests
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker --
+          //ci/ray_ci/... //ci/build/... //release/... //ci/pipeline/... ci
+          --only-tags=release_unit,ci_unit
+          --cache-test-results --parallelism-per-worker 2
+          --build-name forge
+          --build-type skip
+    instance_type: small
+    tags: tools
+  - label: ":coral: reef: raydepsets tests"
+    key: raydepsets-tests
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker --
+          //ci/raydepsets/... ci
+          --cache-test-results
+          --build-name forge
+          --build-type skip
+    instance_type: small
+    tags: tools
+  - label: ":coral: reef: privileged container tests"
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker --
+          //ci/ray_ci:test_privileged ci
+          --cache-test-results
+          --build-name oss-ci-base_test-py3.10
+          --build-type cgroup
+          --privileged
+    instance_type: small
+    depends_on: oss-ci-base_test-multipy(python=3.10)
+    tags: tools
+  - label: ":coral: reef: iwyu tests"
+    commands:
+      - bazel test --config iwyu //bazel/tests/cpp:example_test
+    instance_type: small
+    depends_on: oss-ci-base_build-multipy(python=3.10)
+    job_env: oss-ci-base_build-py3.10
+    tags: tools

.buildkite/copy_files.py

@@ -0,0 +1,127 @@
+import argparse
+import os
+import subprocess
+import sys
+import time
+from collections import OrderedDict
+
+import requests
+from aws_requests_auth.boto_utils import BotoAWSRequestsAuth
+
+
+def retry(f):
+    def inner():
+        resp = None
+        for _ in range(5):
+            resp = f()
+            print("Getting Presigned URL, status_code", resp.status_code)
+            if resp.status_code >= 500:
+                print("errored, retrying...")
+                print(resp.text)
+                time.sleep(5)
+            else:
+                return resp
+        if resp is None or resp.status_code >= 500:
+            print("still errorred after many retries")
+            sys.exit(1)
+
+    return inner
+
+
+@retry
+def perform_auth():
+    auth = BotoAWSRequestsAuth(
+        aws_host="vop4ss7n22.execute-api.us-west-2.amazonaws.com",
+        aws_region="us-west-2",
+        aws_service="execute-api",
+    )
+    resp = requests.get(
+        "https://vop4ss7n22.execute-api.us-west-2.amazonaws.com/endpoint/",
+        auth=auth,
+        params={"job_id": os.environ["BUILDKITE_JOB_ID"]},
+    )
+    return resp
+
+
+def handle_docker_login(resp):
+    pwd = resp.json()["docker_password"]
+    subprocess.check_call(
+        ["docker", "login", "--username", "raydockerreleaser", "--password", pwd]
+    )
+
+
+def gather_paths(dir_path):
+    dir_path = dir_path.replace("/", os.path.sep)
+    assert os.path.exists(dir_path)
+    if os.path.isdir(dir_path):
+        paths = [os.path.join(dir_path, f) for f in os.listdir(dir_path)]
+    else:
+        paths = [dir_path]
+    return paths
+
+
+dest_resp_mapping = {
+    "wheels": "presigned_resp_prod_wheels",
+    "branch_wheels": "presigned_resp_prod_wheels",
+    "jars": "presigned_resp_prod_wheels",
+    "branch_jars": "presigned_resp_prod_wheels",
+    "logs": "presigned_logs",
+}
+
+
+def upload_paths(paths, resp, destination):
+    dest_key = dest_resp_mapping[destination]
+    c = resp.json()[dest_key]
+    of = OrderedDict(c["fields"])
+
+    sha = os.environ["BUILDKITE_COMMIT"]
+    branch = os.environ["BUILDKITE_BRANCH"]
+    bk_job_id = os.environ["BUILDKITE_JOB_ID"]
+
+    current_os = sys.platform
+
+    for path in paths:
+        fn = os.path.split(path)[-1]
+        of["key"] = {
+            "wheels": f"latest/{fn}",
+            "branch_wheels": f"{branch}/{sha}/{fn}",
+            "jars": f"jars/latest/{current_os}/{fn}",
+            "branch_jars": f"jars/{branch}/{sha}/{current_os}/{fn}",
+            "logs": f"bazel_events/{branch}/{sha}/{bk_job_id}/{fn}",
+        }[destination]
+        of["file"] = open(path, "rb")
+        r = requests.post(c["url"], files=of)
+        print(f"Uploaded {path} to {of['key']}", r.status_code)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="Helper script to upload files to S3 bucket"
+    )
+    parser.add_argument("--path", type=str, required=False)
+    parser.add_argument("--destination", type=str)
+    args = parser.parse_args()
+
+    if os.environ.get("RAYCI_SKIP_UPLOAD", "false") == "true":
+        print("Skipping upload.")
+        sys.exit(0)
+
+    assert args.destination in {
+        "branch_jars",
+        "branch_wheels",
+        "jars",
+        "logs",
+        "wheels",
+        "docker_login",
+    }
+    assert "BUILDKITE_JOB_ID" in os.environ
+    assert "BUILDKITE_COMMIT" in os.environ
+
+    resp = perform_auth()
+
+    if args.destination == "docker_login":
+        handle_docker_login(resp)
+    else:
+        paths = gather_paths(args.path)
+        print("Planning to upload", paths)
+        upload_paths(paths, resp, args.destination)

.buildkite/core.rayci.yml

@@ -0,0 +1,670 @@
+group: core tests
+depends_on:
+  - forge
+  - ray-core-build(*)
+  - ray-dashboard-build
+steps:
+  # builds
+  - name: corebuild-multipy
+    label: "wanda: corebuild-py{{array.python}}"
+    wanda: ci/docker/core.build.wanda.yaml
+    tags: cibase
+    array:
+      python:
+        - "3.10"
+        - "3.12"
+    env:
+      PYTHON: "{{array.python}}"
+      BASE_TYPE: "build"
+      BUILD_VARIANT: "build"
+    depends_on: oss-ci-base_build-multipy($)
+
+  - name: coregpubuild-multipy
+    label: "wanda: coregpubuild-py{{array.python}}"
+    wanda: ci/docker/core.build.wanda.yaml
+    tags: cibase
+    depends_on: oss-ci-base_gpu-multipy($)
+    env:
+      PYTHON: "{{array.python}}"
+      BASE_TYPE: "gpu"
+      BUILD_VARIANT: "gpubuild"
+      RAYCI_IS_GPU_BUILD: "true"
+    array:
+      python:
+        - "3.10"
+
+  - name: coregpu-cu130-build-multipy
+    label: "wanda: coregpu-cu130-build-py{{array.python}}"
+    wanda: ci/docker/core.build.wanda.yaml
+    tags: cibase
+    depends_on: oss-ci-base_cu130-multipy($)
+    env:
+      PYTHON: "{{array.python}}"
+      BASE_TYPE: "cu130"
+      BUILD_VARIANT: "gpu-cu130-build"
+      RAYCI_IS_GPU_BUILD: "true"
+    array:
+      python:
+        - "3.10"
+
+  - name: minbuild-core
+    label: "wanda: minbuild-core-py{{array.python}}"
+    wanda: ci/docker/min.build.wanda.yaml
+    depends_on: oss-ci-base_test-multipy($)
+    tags: cibase
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+        - "3.14"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      EXTRA_DEPENDENCY: core
+
+  - wait: ~
+    depends_on:
+      - corebuild-multipy(python=3.10)
+
+  # tests
+  - label: ":ray: core: python tests"
+    tags:
+      - core_python
+      - dashboard
+    instance_type: large
+    parallelism: 4
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... //python/ray/_common/tests/... //python/ray/autoscaler/v2/... core
+        --install-mask all-ray-libraries
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 3
+        --python-version 3.10 --build-name corebuild-py3.10
+        --except-tags custom_setup
+        --install-mask all-ray-libraries
+
+  - label: ":ray: core: python {{array.python}} tests ({{array.worker_id}})"
+    key: core_python_tests
+    if: build.pull_request.labels includes "continuous-build" || pipeline.id == "0189e759-8c96-4302-b6b5-b4274406bf89" || pipeline.id == "018f4f1e-1b73-4906-9802-92422e3badaa"
+    tags:
+      - core_python
+      - dashboard
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... //python/ray/autoscaler/v2/... core
+        --install-mask all-ray-libraries
+        --workers 4 --worker-id "{{array.worker_id}}" --parallelism-per-worker 3
+        --python-version {{array.python}} --build-name corebuild-py{{array.python}}
+        --except-tags custom_setup
+    depends_on: corebuild-multipy($)
+    array:
+      python: ["3.12"]
+      worker_id: ["0", "1", "2", "3"]
+
+  - label: ":ray: core: ray client tests"
+    tags:
+      - ray_client
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/...   core
+        --install-mask all-ray-libraries
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 3
+        --python-version 3.10 --build-name corebuild-py3.10
+        --only-tags ray_client
+
+  # Conditionally runs on premerge via the `redis_tests` tag (see
+  # .buildkite/test.rules.txt) when src/ray/gcs/store_client/ is
+  # modified. Always runs on postmerge.
+  - label: ":ray: core: redis tests"
+    tags:
+      - redis_tests
+      - oss
+    instance_type: large
+    parallelism: 4
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... //python/ray/dag/... //python/ray/autoscaler/v2/... core
+        --install-mask all-ray-libraries
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 3
+        --test-env=TEST_EXTERNAL_REDIS=1
+        --except-tags custom_setup
+        --python-version 3.10 --build-name corebuild-py3.10
+
+  # REP-64 GCS FT with the embedded RocksDB backend. Mirrors the redis
+  # tests above but selects rocksdb-mode via TEST_GCS_ROCKSDB=1 (see
+  # python/ray/tests/conftest.py::_setup_rocksdb_gcs). Conditionally
+  # runs on premerge via the `rocksdb_tests` tag (see
+  # .buildkite/test.rules.txt) when src/ray/gcs/store_client/ or the
+  # rocksdb build config is modified. Always runs on postmerge.
+  - label: ":ray: core: rocksdb tests"
+    tags:
+      - rocksdb_tests
+      - oss
+    instance_type: large
+    parallelism: 4
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... //python/ray/dag/... //python/ray/autoscaler/v2/... core
+        --install-mask all-ray-libraries
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 3
+        --test-env=TEST_GCS_ROCKSDB=1
+        --except-tags custom_setup
+        --python-version 3.10 --build-name corebuild-py3.10
+
+  - label: ":ray: core: memory pressure tests"
+    tags:
+      - core_python
+      - oss
+      - skip-on-premerge
+    instance_type: medium
+    commands:
+      - cleanup() { ./ci/build/upload_build_info.sh; }; trap cleanup EXIT
+      - (cd python/ray/dashboard/client && npm ci && npm run build)
+      - pip install -e python[client]
+      - bazel test --config=ci --jobs=1 $(./ci/run/bazel_export_options)
+        --test_tag_filters=mem_pressure -- //python/ray/tests/...
+    job_env: corebuild-py3.10
+
+  - label: ":ray: core: out of disk tests"
+    tags:
+      - core_python
+      - oss
+    instance_type: small
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... core
+        --python-version 3.10 --build-name corebuild-py3.10
+        --only-tags=tmpfs --tmp-filesystem=tmpfs
+
+  - label: ":ray: core: out of disk redis tests"
+    tags:
+      - redis_tests
+      - oss
+    instance_type: small
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... core
+        --test-env=TEST_EXTERNAL_REDIS=1
+        --only-tags=tmpfs --tmp-filesystem=tmpfs
+        --python-version 3.10 --build-name corebuild-py3.10
+
+  - label: ":ray: core: out of disk rocksdb tests"
+    tags:
+      - rocksdb_tests
+      - oss
+    instance_type: small
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... core
+        --test-env=TEST_GCS_ROCKSDB=1
+        --only-tags=tmpfs --tmp-filesystem=tmpfs
+        --python-version 3.10 --build-name corebuild-py3.10
+
+  - label: ":ray: core: doc tests"
+    if: '!(build.pull_request.labels includes "docs-go")'
+    tags:
+      - core_python
+      - doc
+    instance_type: large
+    commands:
+      # doc tests
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/... //doc/... core
+        --only-tags doctest
+        --python-version 3.10 --build-name corebuild-py3.10
+        --parallelism-per-worker 3
+      # doc examples
+      - bazel run //ci/ray_ci:test_in_docker -- //doc/... core
+        --install-mask all-ray-libraries
+        --except-tags doctest,post_wheel_build,gpu,multi_gpu,mem_pressure
+        --parallelism-per-worker 3
+        --python-version 3.10 --build-name corebuild-py3.10
+        --skip-ray-installation
+      # doc memory pressure example
+      - bazel run //ci/ray_ci:test_in_docker -- //doc/... core
+        --only-tags mem_pressure
+        --except-tags gpu
+        --python-version 3.10 --build-name corebuild-py3.10
+        --skip-ray-installation
+
+  - label: ":ray: core: dask tests"
+    tags:
+      - dask
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker --
+        python/ray/util/dask/... core
+        --install-mask all-ray-libraries
+        --python-version 3.12
+        --build-name datalbuild-py3.12
+    depends_on:
+      - datalbuild-multipy(python=3.12)
+      - forge
+
+  - label: ":ray: core: modin tests"
+    tags:
+      - skip-on-premerge
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker --
+        python/ray/tests/modin/... core
+        --python-version 3.10
+        --build-name datalbuild-py3.10
+    depends_on:
+      - datalbuild-multipy(python=3.10)
+      - forge
+
+  - label: ":ray: core: dashboard tests"
+    tags:
+      - core_python
+      - dashboard
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- python/ray/dashboard/... core
+        --parallelism-per-worker 3
+        --python-version 3.10 --build-name corebuild-py3.10
+      # ui tests
+      - docker run -i --rm --volume /tmp/artifacts:/artifact-mount --shm-size=2.5gb
+        "$${RAYCI_WORK_REPO}":"$${RAYCI_BUILD_ID}"-corebuild-py3.10 /bin/bash -iecuo pipefail
+        "./python/ray/dashboard/tests/run_ui_tests.sh"
+
+  - label: ":ray: core: debug tests"
+    tags:
+      - core_python
+      - skip-on-premerge
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... core
+        --install-mask all-ray-libraries
+        --build-type debug
+        --parallelism-per-worker 3
+        --python-version 3.10 --build-name corebuild-py3.10
+        --only-tags debug_tests
+        --except-tags kubernetes,manual
+
+  - label: ":ray: core: asan tests"
+    tags:
+      - core_python
+      - skip-on-premerge
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... core
+        --install-mask all-ray-libraries
+        --build-type asan
+        --parallelism-per-worker 2
+        --python-version 3.10 --build-name corebuild-py3.10
+        --only-tags asan_tests
+        --except-tags kubernetes,manual
+
+  - label: ":ray: core: wheel tests"
+    key: core-wheel-tests
+    tags: linux_wheels
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... //doc/... core
+        --install-mask all-ray-libraries
+        --build-type wheel
+        --parallelism-per-worker 3
+        --python-version 3.10 --build-name corebuild-py3.10
+        --only-tags post_wheel_build
+        --test-env=RAY_CI_POST_WHEEL_TESTS=True
+    depends_on:
+      - manylinux-x86_64
+      - corebuild-multipy(python=3.10)
+      - forge
+      - ray-wheel-build(python=3.10)
+
+  # Premerge runs only the lowest and highest supported Python versions. The
+  # intermediate versions are covered by the postmerge-only step below.
+  - label: ":ray: core: minimal tests {{array.python}}"
+    key: core_minimal_tests
+    tags:
+      - core_python
+      - dashboard
+      - oss
+      - min_build
+    instance_type: medium
+    commands:
+      # validate minimal installation
+      - python ./ci/env/check_minimal_install.py
+      # core tests
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... //python/ray/dashboard/... core
+        --parallelism-per-worker 3
+        --python-version {{array.python}}
+        --build-name minbuild-core-py{{array.python}}
+        --test-env=RAY_MINIMAL=1
+        --test-env=EXPECTED_PYTHON_VERSION={{array.python}}
+        --only-tags minimal
+        --except-tags basic_test,manual,cgroup
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... //python/ray/dashboard/... core
+        --parallelism-per-worker 3
+        --python-version {{array.python}}
+        --build-name minbuild-core-py{{array.python}}
+        --test-env=RAY_MINIMAL=1
+        --test-env=EXPECTED_PYTHON_VERSION={{array.python}}
+        --only-tags minimal
+        --except-tags no_basic_test,manual
+        --skip-ray-installation
+      # core redis tests
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... //python/ray/dashboard/... core
+        --parallelism-per-worker 3
+        --python-version {{array.python}}
+        --build-name minbuild-core-py{{array.python}}
+        --test-env=RAY_MINIMAL=1
+        --test-env=TEST_EXTERNAL_REDIS=1
+        --test-env=EXPECTED_PYTHON_VERSION={{array.python}}
+        --only-tags minimal
+        --except-tags no_basic_test,manual
+        --skip-ray-installation
+      # serve tests
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... //python/ray/dashboard/... serve
+        --parallelism-per-worker 3
+        --python-version {{array.python}}
+        --build-name minbuild-core-py{{array.python}}
+        --test-env=RAY_MINIMAL=1
+        --only-tags minimal
+        --skip-ray-installation
+    depends_on:
+      - minbuild-core($)
+    array:
+      python:
+        - "3.10"
+        - "3.14"
+
+  # Intermediate Python versions only run on postmerge (skipped on premerge).
+  - label: ":ray: core: minimal tests {{array.python}}"
+    key: core_minimal_tests_postmerge
+    tags:
+      - python
+      - dashboard
+      - oss
+      - min_build
+      - skip-on-premerge
+    instance_type: medium
+    commands:
+      # validate minimal installation
+      - python ./ci/env/check_minimal_install.py
+      # core tests
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... //python/ray/dashboard/... core
+        --parallelism-per-worker 3
+        --python-version {{array.python}}
+        --build-name minbuild-core-py{{array.python}}
+        --test-env=RAY_MINIMAL=1
+        --test-env=EXPECTED_PYTHON_VERSION={{array.python}}
+        --only-tags minimal
+        --except-tags basic_test,manual,cgroup
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... //python/ray/dashboard/... core
+        --parallelism-per-worker 3
+        --python-version {{array.python}}
+        --build-name minbuild-core-py{{array.python}}
+        --test-env=RAY_MINIMAL=1
+        --test-env=EXPECTED_PYTHON_VERSION={{array.python}}
+        --only-tags minimal
+        --except-tags no_basic_test,manual
+        --skip-ray-installation
+      # core redis tests
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... //python/ray/dashboard/... core
+        --parallelism-per-worker 3
+        --python-version {{array.python}}
+        --build-name minbuild-core-py{{array.python}}
+        --test-env=RAY_MINIMAL=1
+        --test-env=TEST_EXTERNAL_REDIS=1
+        --test-env=EXPECTED_PYTHON_VERSION={{array.python}}
+        --only-tags minimal
+        --except-tags no_basic_test,manual
+        --skip-ray-installation
+      # serve tests
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... //python/ray/dashboard/... serve
+        --parallelism-per-worker 3
+        --python-version {{array.python}}
+        --build-name minbuild-core-py{{array.python}}
+        --test-env=RAY_MINIMAL=1
+        --only-tags minimal
+        --skip-ray-installation
+    depends_on:
+      - minbuild-core($)
+    array:
+      python:
+        - "3.11"
+        - "3.12"
+        - "3.13"
+
+  - label: ":ray: core: cgroup tests"
+    tags:
+      - core_cpp
+      - core_python
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //:all
+        //python/ray/tests/resource_isolation:test_resource_isolation_integration
+        //python/ray/tests/resource_isolation:test_resource_isolation_config core
+        --privileged --cache-test-results
+        --python-version 3.10 --build-name corebuild-py3.10
+      - bazel run //ci/ray_ci:test_in_docker -- //:all //src/ray/common/cgroup2/tests/... core
+        --build-type clang --cache-test-results
+        --python-version 3.10 --build-name corebuild-py3.10
+      - docker run --privileged -i --rm --volume /tmp/artifacts:/artifact-mount --shm-size=2.5gb
+        "$${RAYCI_WORK_REPO}":"$${RAYCI_BUILD_ID}"-corebuild-py3.10 /bin/bash
+        "./src/ray/common/cgroup2/integration_tests/sysfs_cgroup_driver_integration_test_entrypoint.sh"
+
+  - label: ":ray: core: cpp tests"
+    tags: core_cpp
+
+    instance_type: medium
+    commands:
+      - RAYCI_DISABLE_TEST_DB=1 bazel run //ci/ray_ci:test_in_docker --
+        //:all //src/... core --except-tags=cgroup --build-type clang
+        --python-version 3.10 --build-name corebuild-py3.10
+        --cache-test-results --parallelism-per-worker 2
+
+  # block on premerge and microcheck
+  - block: "run cpp sanitizer tests"
+    if: build.env("BUILDKITE_PIPELINE_ID") == "0189942e-0876-4b8f-80a4-617f988ec59b" || build.env("BUILDKITE_PIPELINE_ID") == "018f4f1e-1b73-4906-9802-92422e3badaa"
+    key: block-core-cpp-sanitizer-tests
+    depends_on: []
+
+  - label: ":ray: core: cpp asan tests"
+    tags: core_cpp
+    instance_type: medium
+    commands:
+      - RAYCI_DISABLE_TEST_DB=1 bazel run //ci/ray_ci:test_in_docker -- //:all //src/... core --except-tags=cgroup
+        --build-type asan-clang --cache-test-results --parallelism-per-worker 2
+        --python-version 3.10 --build-name corebuild-py3.10
+    depends_on:
+      - block-core-cpp-sanitizer-tests
+      - corebuild-multipy(python=3.10)
+
+  - label: ":ray: core: cpp ubsan tests"
+    tags: core_cpp
+    instance_type: large
+    commands:
+      - RAYCI_DISABLE_TEST_DB=1 bazel run //ci/ray_ci:test_in_docker -- //:all //src/... core
+        --python-version 3.10 --build-name corebuild-py3.10
+        --build-type ubsan --except-tags no_ubsan,cgroup
+        --cache-test-results --parallelism-per-worker 2
+    depends_on:
+      - block-core-cpp-sanitizer-tests
+      - corebuild-multipy(python=3.10)
+
+  - label: ":ray: core: cpp tsan tests"
+    tags: core_cpp
+    instance_type: medium
+    commands:
+      - RAYCI_DISABLE_TEST_DB=1 bazel run //ci/ray_ci:test_in_docker -- //:all //src/... core
+        --python-version 3.10 --build-name corebuild-py3.10
+        --build-type tsan-clang --except-tags no_tsan,cgroup
+        --cache-test-results --parallelism-per-worker 2
+    depends_on:
+      - block-core-cpp-sanitizer-tests
+      - corebuild-multipy(python=3.10)
+
+  - block: "run dag tests"
+    key: block-dag-tests
+    depends_on: []
+
+  - label: ":ray: core: dag tests"
+    key: core_dag_tests
+    tags:
+      - core_python
+      - cgraphs_direct_transport
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/dag/... core
+        --install-mask all-ray-libraries
+        --python-version 3.10 --build-name corebuild-py3.10
+        --only-tags ray_dag_tests,compiled_graphs
+        --except-tags custom_setup
+    depends_on:
+      - block-dag-tests
+      - corebuild-multipy(python=3.10)
+
+  - label: ":ray: core: flaky tests"
+    key: core_flaky_tests
+    tags:
+      - core_python
+      - flaky
+      - skip-on-premerge
+    instance_type: large
+    soft_fail: true
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/... //doc/... core
+        --python-version 3.10 --build-name corebuild-py3.10
+        --install-mask all-ray-libraries
+        --run-flaky-tests
+        --except-tags multi_gpu,cgroup
+    depends_on:
+      - corebuild-multipy(python=3.10)
+
+  - label: ":ray: core: flaky gpu tests"
+    key: core_flaky_gpu_tests
+    tags:
+      - gpu
+      - core_python
+      - skip-on-premerge
+    instance_type: gpu-large
+    soft_fail: true
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/... //python/ray/dag/... //doc/... core
+        --install-mask all-ray-libraries
+        --run-flaky-tests
+        --gpus 4
+        --build-name coregpubuild-py3.10
+        --python-version 3.10
+        --only-tags multi_gpu
+    depends_on: coregpubuild-multipy(python=3.10)
+
+  - label: ":ray: core: cpp worker tests"
+    tags:
+      - core_cpp
+      - cpp
+      - oss
+    instance_type: medium
+    commands:
+      - if [[ "$${BUILDKITE_CACHE_READONLY:-}" == "true" ]]; then
+          echo "build --remote_upload_local_results=false" >> ~/.bazelrc;
+        fi
+      # cpp worker tests has one that tests cross-language with Java.
+      - RAY_INSTALL_JAVA=1 ci/ci.sh build
+      - ci/ci.sh test_cpp
+    depends_on: oss-ci-base_build-multipy(python=3.10)
+    job_env: oss-ci-base_build-py3.10
+
+  - label: ":ray: core: java worker tests"
+    tags:
+      - java
+      - core_python
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... core
+        --python-version 3.10 --build-name corebuild-py3.10
+        --build-type java
+        --only-tags needs_java
+    depends_on: corebuild-multipy(python=3.10)
+
+  - label: ":ray: core: HA integration tests"
+    tags:
+      - core_python
+      - docker
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:build_in_docker -- docker --python-version 3.10
+        --platform cpu --canonical-tag ha_integration
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... core --only-tags ha_integration
+        --python-version 3.10 --build-name corebuild-py3.10
+    depends_on:
+      - manylinux-x86_64
+      - forge
+      - raycpubase(python=3.10)
+      - corebuild-multipy(python=3.10)
+
+  - label: ":ray: core: runtime env container tests"
+    tags:
+      - docker
+      - runtime_env_container
+      - oss
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:build_in_docker -- docker --python-version 3.10
+        --platform cpu --canonical-tag test_container
+      - docker build --progress=plain --build-arg BASE_IMAGE="rayproject/ray:test_container"
+        -t rayproject/ray:runtime_env_container -f ci/docker/runtime_env_container/Dockerfile .
+      # Disable test DB, these tests will never succeed if run in the flaky step.
+      - RAYCI_DISABLE_TEST_DB=1 bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... core
+        --python-version 3.10 --build-name corebuild-py3.10
+        --install-mask all-ray-libraries
+        --only-tags runtime_env_container
+    depends_on:
+      - manylinux-x86_64
+      - forge
+      - raycpubase(python=3.10)
+      - corebuild-multipy(python=3.10)
+
+  - label: ":core: core: spark-on-ray tests"
+    # NOTE: The Spark-on-Ray tests intentionally aren't triggered by the `java` tag to
+    # avoid running them for every C++ code change.
+    tags:
+      - spark_on_ray
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... core
+        --build-type debug
+        --test-env=RAY_ON_SPARK_BACKGROUND_JOB_STARTUP_WAIT=1
+        --test-env=RAY_ON_SPARK_RAY_WORKER_NODE_STARTUP_INTERVAL=5
+        --only-tags spark_on_ray
+        --python-version 3.10 --build-name corebuild-py3.10
+    depends_on:
+      - corebuild-multipy(python=3.10)
+
+  # block gpu tests on premerge and microcheck
+  - block: "run multi gpu tests"
+    if: build.env("BUILDKITE_PIPELINE_ID") == "0189942e-0876-4b8f-80a4-617f988ec59b" || build.env("BUILDKITE_PIPELINE_ID") == "018f4f1e-1b73-4906-9802-92422e3badaa"
+    key: block-core-gpu-tests
+    depends_on: []
+
+  - label: ":ray: core: multi gpu tests"
+    key: core-multi-gpu-tests
+    tags:
+      - cgraphs_direct_transport
+      - gpu
+    instance_type: gpu-large
+    # we're running some cgraph doc tests here as well since they need gpus
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... //python/ray/dag/... //doc/... core
+        --gpus 4
+        --build-name coregpubuild-py3.10
+        --python-version 3.10
+        --only-tags multi_gpu
+        --install-mask all-ray-libraries
+    depends_on:
+      - block-core-gpu-tests
+      - coregpubuild-multipy(python=3.10)
+
+  - label: ":ray: core: multi gpu cu130 tests"
+    key: core-multi-gpu-cu130-tests
+    tags:
+      - cgraphs_direct_transport
+      - gpu
+    instance_type: gpu-large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... //python/ray/dag/... //doc/... core
+        --gpus 4
+        --build-name coregpu-cu130-build-py3.10
+        --python-version 3.10
+        --only-tags multi_gpu
+        --install-mask all-ray-libraries
+    depends_on:
+      - block-core-gpu-tests
+      - coregpu-cu130-build-multipy(python=3.10)

.buildkite/data.rayci.yml

@@ -0,0 +1,379 @@
+group: data tests
+depends_on:
+  - forge
+  - oss-ci-base_ml-multipy(*)
+  - ray-core-build(*)
+  - ray-dashboard-build
+steps:
+  # builds
+  - name: data17build-multipy
+    label: "wanda: data17build-py{{array.python}}"
+    wanda: ci/docker/data17.build.wanda.yaml
+    array:
+      python:
+        - "3.10"
+    env:
+      PYTHON: "{{array.python}}"
+    tags: cibase
+
+  - name: datalbuild-multipy
+    label: "wanda: datalbuild-py{{array.python}}"
+    wanda: ci/docker/datal.build.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.12"
+    env:
+      PYTHON: "{{array.python}}"
+    tags: cibase
+
+  - name: datanbuild-multipy
+    wanda: ci/docker/datan.build.wanda.yaml
+    env:
+      PYTHON: "3.10"
+    tags: cibase
+
+  - name: datamongobuild-multipy
+    label: "wanda: datamongobuild-py3.10"
+    wanda: ci/docker/datamongo.build.wanda.yaml
+    env:
+      PYTHON: "3.10"
+    tags: cibase
+
+  - name: datatfdsbuild-multipy
+    label: "wanda: datatfdsbuild-py3.12"
+    wanda: ci/docker/datatfds.build.wanda.yaml
+    env:
+      PYTHON: "3.12"
+    tags: cibase
+
+  - name: docgpubuild-py312
+    label: "wanda: docgpubuild-py3.12"
+    wanda: ci/docker/docgpu.build.wanda.yaml
+    env:
+      PYTHON: "3.12"
+    depends_on: oss-ci-base_gpu-multipy(python=3.12)
+    tags: cibase
+
+  # type check
+  - label: ":python: pyrefly type check"
+    tags:
+      - data
+    instance_type: small
+    commands:
+      - bash ci/lint/pyrefly-check.sh
+    depends_on: data17build-multipy(python=3.10)
+    job_env: data17build-py3.10
+
+  # tests
+  - label: ":database: data: arrow v17 tests"
+    tags:
+      - data
+    instance_type: large
+    parallelism: 8
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/data/... //python/ray/air/... data
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}"
+        --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 3
+        --build-name data17build-py3.10 --python-version 3.10
+        --except-tags data_integration,doctest,data_non_parallel,dask,needs_credentials,tensorflow_datasets,cudf
+    depends_on: data17build-multipy(python=3.10)
+
+  - label: ":database: data: tensorflow-datasets tests"
+    key: data_tensorflow_datasets_tests
+    tags:
+      - data
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/data/... data
+        --build-name datatfdsbuild-py3.12 --python-version 3.12
+        --only-tags tensorflow_datasets
+    depends_on: datatfdsbuild-multipy
+
+  - label: ":database: data: arrow v17 tests (data_non_parallel)"
+    tags:
+      - data
+      - data_non_parallel
+    instance_type: medium
+    parallelism: 3
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/data/... //python/ray/air/... data
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}"
+        --worker-id "$${BUILDKITE_PARALLEL_JOB}"
+        --build-name data17build-py3.10 --python-version 3.10
+        --only-tags data_non_parallel
+        --except-tags data_non_parallel_postmerge_only,cudf
+    depends_on: data17build-multipy(python=3.10)
+
+  - label: ":database: data: arrow v23 tests"
+    tags:
+      - data
+      - skip-on-premerge
+    instance_type: medium
+    parallelism: 8
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/data/... //python/ray/air/... data
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}"
+        --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 3
+        --build-name datalbuild-py3.10 --python-version 3.10
+        --except-tags data_integration,doctest,data_non_parallel,dask,needs_credentials,tensorflow_datasets,cudf
+    depends_on: datalbuild-multipy(python=3.10)
+
+  - label: ":database: data: arrow v23 tests (data_non_parallel)"
+    tags:
+      - data
+      - data_non_parallel
+      - skip-on-premerge
+    instance_type: medium
+    parallelism: 3
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/data/... //python/ray/air/... data
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}"
+        --worker-id "$${BUILDKITE_PARALLEL_JOB}"
+        --build-name datalbuild-py3.10 --python-version 3.10
+        --only-tags data_non_parallel
+        --except-tags data_non_parallel_postmerge_only,cudf
+    depends_on: datalbuild-multipy(python=3.10)
+
+  - label: ":database: data: arrow v23 py{{array.python}} tests ({{array.worker_id}})"
+    key: datal_python_tests
+    if: build.pull_request.labels includes "continuous-build" || pipeline.id == "0189e759-8c96-4302-b6b5-b4274406bf89" || pipeline.id == "018f4f1e-1b73-4906-9802-92422e3badaa"
+    tags:
+      - data
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/data/... //python/ray/air/... data
+        --workers 2 --worker-id {{array.worker_id}} --parallelism-per-worker 3
+        --build-name datalbuild-py{{array.python}} --python-version {{array.python}}
+        --except-tags data_integration,doctest,data_non_parallel,dask,needs_credentials,tensorflow_datasets,cudf
+    depends_on: datalbuild-multipy($)
+    array:
+      python: ["3.12"]
+      worker_id: ["0", "1"]
+
+  - label: ":database: data: arrow v23 py{{array.python}} tests (data_non_parallel)"
+    key: datal_python_non_parallel_tests
+    if: build.pull_request.labels includes "continuous-build" || pipeline.id == "0189e759-8c96-4302-b6b5-b4274406bf89" || pipeline.id == "018f4f1e-1b73-4906-9802-92422e3badaa"
+    tags:
+      - data
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/data/... //python/ray/air/... data
+        --build-name datalbuild-py{{array.python}} --python-version {{array.python}}
+        --only-tags data_non_parallel
+        --except-tags data_non_parallel_postmerge_only,cudf
+    depends_on: datalbuild-multipy($)
+    array:
+      python: ["3.12"]
+
+  - label: ":database: data: arrow nightly tests"
+    tags:
+      - data
+      - skip-on-premerge
+      - oss
+      - disabled
+    instance_type: medium
+    parallelism: 2
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/data/... //python/ray/air/... data
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}"
+        --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 3
+        --build-name datanbuild-py3.10 --python-version 3.10
+        --except-tags data_integration,doctest,data_non_parallel,dask,needs_credentials,tensorflow_datasets,cudf
+    depends_on: datanbuild-multipy
+    soft_fail: true
+
+  - label: ":database: data: arrow nightly tests (data_non_parallel)"
+    tags:
+      - data
+      - skip-on-premerge
+      - oss
+      - disabled
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/data/... //python/ray/air/... data
+        --build-name datanbuild-py3.10 --python-version 3.10
+        --only-tags data_non_parallel
+        --except-tags data_non_parallel_postmerge_only,cudf
+    depends_on: datanbuild-multipy
+    soft_fail: true
+
+  - label: ":database: data: postmerge arrow v17 tests"
+    tags:
+      - data
+      - skip-on-premerge
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/data/... //python/ray/air/... data
+        --build-name data17build-py3.10 --python-version 3.10
+        --only-tags data_non_parallel_postmerge_only
+    depends_on: data17build-multipy(python=3.10)
+
+  - label: ":database: data: postmerge arrow v23 tests"
+    tags:
+      - data
+      - skip-on-premerge
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/data/... //python/ray/air/... data
+        --build-name datalbuild-py3.10 --python-version 3.10
+        --only-tags data_non_parallel_postmerge_only
+    depends_on: datalbuild-multipy(python=3.10)
+
+  - label: ":database: data: dask tests"
+    tags:
+      - data
+      - dask
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/data/... data
+        --build-name datalbuild-py3.12 --python-version 3.12
+        --only-tags dask
+    depends_on: datalbuild-multipy(python=3.12)
+
+  - label: ":database: data: doc tests"
+    if: '!(build.pull_request.labels includes "docs-go")'
+    tags:
+      - data
+      - doc
+    instance_type: medium
+    commands:
+      # doc tests
+      - bazel run //ci/ray_ci:test_in_docker -- python/ray/... //doc/... data
+        --build-name datalbuild-py3.10
+        --python-version 3.10
+        --except-tags gpu
+        --only-tags doctest
+        --parallelism-per-worker 2
+      # doc examples
+      - bazel run //ci/ray_ci:test_in_docker -- //doc/... data
+        --build-name datalbuild-py3.10
+        --python-version 3.10
+        --except-tags gpu,post_wheel_build,doctest,dask
+        --parallelism-per-worker 2
+        --skip-ray-installation
+    depends_on: datalbuild-multipy(python=3.10)
+
+  - label: ":database: data: dask doc tests"
+    if: '!(build.pull_request.labels includes "docs-go")'
+    tags:
+      - data
+      - doc
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //doc/... data
+        --build-name datalbuild-py3.12
+        --python-version 3.12
+        --only-tags dask
+        --parallelism-per-worker 2
+    depends_on: datalbuild-multipy(python=3.12)
+
+  - label: ":database: data: doc gpu tests"
+    if: '!(build.pull_request.labels includes "docs-go")'
+    tags:
+      - data
+      - doc
+      - gpu
+    instance_type: gpu-large
+    commands:
+      # doc tests
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/data/... //doc/... data
+        --build-name docgpubuild-py3.10
+        --only-tags doctest
+        --except-tags cpu
+        --python-version 3.10
+      # doc examples
+      - bazel run //ci/ray_ci:test_in_docker -- //doc/... data
+        --build-name docgpubuild-py3.10
+        --except-tags doctest
+        --only-tags gpu
+        --skip-ray-installation
+        --python-version 3.10
+    depends_on: docgpubuild
+
+  - label: ":database: data: cuDF batch format tests"
+    tags:
+      - data
+      - gpu
+      - cudf
+    instance_type: gpu-large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/data/... data
+        --build-name docgpubuild-py3.12
+        --only-tags cudf
+        --gpus 1
+        --python-version 3.12
+    depends_on: docgpubuild-py312
+
+  - label: ":database: data: integration tests"
+    tags:
+      - data
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/data/... data
+        --build-name datamongobuild-py3.10
+        --python-version 3.10
+        --build-type java
+        --only-tags data_integration
+        --except-tags doctest
+    depends_on: datamongobuild-multipy
+
+  - label: ":database: data: dashboard tests"
+    tags:
+      - data
+      - dashboard
+    instance_type: small
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- python/ray/dashboard/... data
+        --build-name datalbuild-py3.10
+        --python-version 3.10
+        --parallelism-per-worker 3
+    depends_on: datalbuild-multipy(python=3.10)
+
+  - label: ":database: data: flaky tests"
+    key: data_flaky_tests
+    tags:
+      - data
+      - flaky
+      - skip-on-premerge
+    instance_type: medium
+    soft_fail: true
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //... data --run-flaky-tests
+        --parallelism-per-worker 3
+        --build-name datalbuild-py3.10
+        --python-version 3.10
+        --except-tags gpu_only,gpu
+    depends_on: datalbuild-multipy(python=3.10)
+
+  - label: ":database: data: flaky gpu tests"
+    key: data_flaky_gpu_tests
+    tags:
+      - data
+      - skip-on-premerge
+    instance_type: gpu-large
+    soft_fail: true
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //... data --run-flaky-tests
+        --build-name docgpubuild-py3.10
+        --only-tags gpu,gpu_only
+        --python-version 3.10
+    depends_on: docgpubuild
+
+  - label: ":database: data: postmerge authenticated tests"
+    key: data_postmerge_authenticated_tests
+    tags:
+      - data
+      - oss
+      - skip-on-premerge
+    instance_type: medium
+    commands:
+      - $(python ci/env/setup_credentials.py)
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/data/... data
+        --build-name datalbuild-py3.10
+        --python-version 3.10
+        --only-tags needs_credentials
+        --test-env=SNOWFLAKE_USER --test-env=SNOWFLAKE_ACCOUNT
+        --test-env=SNOWFLAKE_DATABASE --test-env=SNOWFLAKE_SCHEMA
+        --test-env=SNOWFLAKE_WAREHOUSE --test-env=SNOWFLAKE_PRIVATE_KEY
+    depends_on: datalbuild-multipy(python=3.10)

.buildkite/dependencies.rayci.yml

@@ -0,0 +1,45 @@
+group: dependencies
+depends_on:
+  - forge
+steps:
+  # dependencies
+  - label: ":tapioca: build: pip-compile dependencies"
+    key: pip_compile_dependencies
+    tags: python_dependencies
+    instance_type: small
+    commands:
+      # uncomment the following line to update the pinned versions of pip dependencies
+      # to the latest versions; otherwise, the pinned versions will be re-used as much
+      # as possible
+      # - rm ./python/requirements_compiled.txt
+      - cp ./python/requirements_compiled.txt requirements_compiled_backup.txt
+      - ./ci/ci.sh compile_pip_dependencies
+      - cp -f ./python/requirements_compiled.txt /artifact-mount/
+      - diff ./python/requirements_compiled.txt requirements_compiled_backup.txt || (echo "requirements_compiled.txt is not up to date. Please download it from Artifacts tab and git push the changes." && exit 1)
+    job_env: oss-ci-base_test-py3.11
+    depends_on: oss-ci-base_test-multipy(python=3.11)
+
+  - label: ":tapioca: build: pip-compile py3.13 dependencies"
+    key: pip_compile_313_dependencies
+    tags: python_dependencies
+    instance_type: small
+    commands:
+      # uncomment the following line to update the pinned versions of pip dependencies
+      # to the latest versions; otherwise, the pinned versions will be re-used as much
+      # as possible
+      # - rm ./python/requirements_compiled_py3.13.txt
+      - cp ./python/requirements_compiled_py3.13.txt requirements_compiled_py3.13_backup.txt
+      - ./ci/ci.sh compile_313_pip_dependencies
+      - cp -f ./python/requirements_compiled_py3.13.txt /artifact-mount/
+      - diff ./python/requirements_compiled_py3.13.txt requirements_compiled_py3.13_backup.txt || (echo "requirements_compiled_py3.13.txt is not up to date. Please download it from Artifacts tab and git push the changes." && exit 1)
+    job_env: oss-ci-base_test-py3.11
+    depends_on: oss-ci-base_test-multipy(*)
+
+  - label: ":tapioca: build: raydepsets: compile all dependencies"
+    key: raydepsets_compile_all_dependencies
+    tags: python_dependencies
+    instance_type: small
+    commands:
+      - bazel run //ci/raydepsets:raydepsets -- build --all-configs --check
+    job_env: manylinux-x86_64
+    depends_on: manylinux-x86_64

.buildkite/doc.rayci.yml

@@ -0,0 +1,93 @@
+group: doc
+steps:
+  - name: docbuild
+    label: "wanda: docbuild-py{{matrix}}"
+    wanda: ci/docker/doc.build.wanda.yaml
+    depends_on:
+      - oss-ci-base_build-multipy(python=3.11)
+      - ray-core-build(python=3.11)
+      - ray-dashboard-build
+    matrix:
+      - "3.11"
+    env:
+      PYTHON: "{{matrix}}"
+      REQUIREMENTS_FILE: "python/deplocks/docs/docbuild_depset_py{{matrix}}.lock"
+    tags: cibase
+
+  - name: docgpubuild
+    label: "wanda: docgpubuild-py3.10"
+    wanda: ci/docker/docgpu.build.wanda.yaml
+    depends_on: oss-ci-base_gpu-multipy(python=3.10)
+    env:
+      PYTHON: "3.10"
+    tags: cibase
+
+  - label: ":book: doc: build"
+    key: doc_build
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci/doc:cmd_build
+    depends_on: docbuild
+    job_env: docbuild-py3.11
+    tags:
+      - oss
+      - doc
+      - skip-on-premerge
+
+  - label: ":book: doc: check API annotations"
+    if: '!(build.pull_request.labels includes "docs-go")'
+    tags:
+      - oss
+      - core_python
+      - dashboard
+      - ray_client
+      - data
+      - serve
+      - ml
+      - tune
+      - train
+      - llm
+      - rllib
+      - rllib_gpu
+      - doc
+    key: doc_api_annotations
+    instance_type: medium
+    depends_on: docbuild
+    job_env: docbuild-py3.11
+    commands:
+      - bash ci/lint/lint.sh api_annotations
+
+  - label: ":book: doc: check API doc consistency"
+    if: '!(build.pull_request.labels includes "docs-go")'
+    tags:
+      - oss
+      - core_python
+      - dashboard
+      - ray_client
+      - data
+      - serve
+      - ml
+      - tune
+      - train
+      - llm
+      - rllib
+      - rllib_gpu
+      - doc
+    key: doc_api_policy_check
+    instance_type: medium
+    depends_on: docbuild
+    job_env: docbuild-py3.11
+    commands:
+      - bash ci/lint/lint.sh api_policy_check
+
+  - label: ":book: doc: linkcheck"
+    key: doc_linkcheck
+    instance_type: medium
+    commands:
+      - make -C doc/ linkcheck_all
+    depends_on: docbuild
+    job_env: docbuild-py3.11
+    tags:
+      - oss
+      - skip-on-premerge
+    soft_fail: true

.buildkite/hooks/post-artifact

@@ -0,0 +1,31 @@
+#!/bin/bash
+# This script is executed by Buildkite on the host machine.
+# In contrast, our build jobs are run in Docker containers.
+# This means that even though our build jobs write to
+# `/artifact-mount`, the directory on the host machine is
+# actually `/tmp/artifacts`.
+# We clean up the artifacts directory before any command and
+# after uploading artifacts to make sure no stale artifacts
+# remain on the node when a Buildkite runner is re-used.
+set -ex
+if [ -d "/tmp/artifacts" ]; then
+    echo "Cleaning up artifacts after upload."
+    echo "Artifact directory contents before cleanup:"
+    find /tmp/artifacts -print || true
+
+    if [ "$(ls -A /tmp/artifacts)" ]; then
+      echo "Directory not empty, cleaning up..."
+      if [[ "${OSTYPE}" = darwin* ]]; then
+        rm -rf /tmp/artifacts
+        mkdir -p /tmp/artifacts
+      else
+        # Need to run in docker to avoid permission issues
+        docker run --rm -v /tmp/artifacts:/artifact-mount alpine:latest /bin/sh -c 'rm -rf /artifact-mount/*; rm -rf /artifact-mount/.[!.]*' || true
+      fi
+    else
+      echo "Directory already empty, no need to clean up."
+    fi
+
+    echo "Artifact directory contents after cleanup:"
+    find /tmp/artifacts -print || true
+fi

.buildkite/hooks/post-command

@@ -0,0 +1,33 @@
+#!/bin/bash
+# This script is executed by Buildkite on the host machine.
+# In contrast, our build jobs are run in Docker containers.
+# This means that even though our build jobs write to
+# `/artifact-mount`, the directory on the host machine is
+# actually `/tmp/artifacts`.
+# Here, we cat all text files in artifact-mount/test-summaries
+# and upload them as a Buildkite annotation.
+# These files contain a condensed summary of all failing pytest
+# tests to make it easy for users to see which tests are failing.
+# Because we upload them to Buildkite, we don't need to
+# upload them as artifacts and delete them afterwards.
+set -ex
+
+if [ -d "/tmp/artifacts/test-summaries" ] && [ "$(ls -A /tmp/artifacts/test-summaries)" ]; then
+    # Only upload annotations if there are at least 2 files in the directory:
+    # 1 header and 1 failed test.
+    if [ "$(find /tmp/artifacts/test-summaries -maxdepth 1 -name '*.txt' | wc -l)" -ge 2 ]; then
+      echo "Test summaries for ${BUILDKITE_JOB_ID} ${BUILDKITE_LABEL}" | buildkite-agent annotate --job "${BUILDKITE_JOB_ID}" --style error --context "${BUILDKITE_JOB_ID}"
+      cat /tmp/artifacts/test-summaries/*.txt | head -n 20 | buildkite-agent annotate --job "${BUILDKITE_JOB_ID}" --append --style error --context "${BUILDKITE_JOB_ID}"
+    fi
+
+    # Remove test summaries files (don't actually upload as artifacts)
+    # This has to be done with docker to avoid permission issues
+    echo "--- Cleaning up"
+    docker run --rm -v /tmp/artifacts:/artifact-mount alpine:latest /bin/sh -c 'rm -rf /artifact-mount/test-summaries' || true
+fi
+
+# clean up bazel logs if any, this only has effect when the bazel test runs in the same
+# environment as the buildkite job commands, and has no effect when the tests run
+# inside another test container
+rm -rf /tmp/bazel_event_logs
+rm -rf /tmp/artifacts/test-summaries

.buildkite/hooks/pre-command

@@ -0,0 +1,38 @@
+#!/bin/bash
+# This script is executed by Buildkite on the host machine.
+# In contrast, our build jobs are run in Docker containers.
+# This means that even though our build jobs write to
+# `/artifact-mount`, the directory on the host machine is
+# actually `/tmp/artifacts`.
+# We clean up the artifacts directory before any command and
+# after uploading artifacts to make sure no stale artifacts
+# remain on the node when a Buildkite runner is re-used.
+set -ex
+
+echo "Creating artifact directory..."
+if [[ "${OSTYPE}" == linux* ]]; then
+  if [[ -d "/tmp/artifacts" ]]; then
+      echo "Cleaning up old artifacts before command."
+      echo "Artifact directory contents before cleanup:"
+      find /tmp/artifacts -print || true
+
+      if [[ "$(ls -A /tmp/artifacts)" ]]; then
+        echo "Directory not empty, cleaning up..."
+        # Need to run in docker to avoid permission issues
+        docker run --rm -v /tmp/artifacts:/artifact-mount alpine:latest /bin/sh -c 'rm -rf /artifact-mount/*; rm -rf /artifact-mount/.[!.]*' || true
+      else
+        echo "Directory already empty, no need to clean up."
+      fi
+  fi
+
+  docker run --rm -v /tmp/artifacts:/artifact-mount alpine:latest /bin/sh -c 'chown -R 2000 /artifact-mount/' || true
+elif [[ "${OSTYPE}" == msys ]]; then
+  if [[ -d "/c/tmp/artifacts" ]]; then
+    rm -rf /c/tmp/artifacts/*
+  fi
+  mkdir -p /c/tmp/artifacts
+fi
+
+
+RAYCI_CHECKOUT_DIR="$(pwd)"
+export RAYCI_CHECKOUT_DIR

.buildkite/kuberay.rayci.yml

@@ -0,0 +1,51 @@
+group: "kuberay tests"
+steps:
+  - name: k8sbuild
+    wanda: ci/docker/k8s.build.wanda.yaml
+    depends_on:
+      - oss-ci-base_build-multipy(python=3.10)
+    tags: cibase
+
+  - label: ":kubernetes: operator"
+    tags:
+      - core_python
+      - docker
+    instance_type: large
+    commands:
+      - bash ci/k8s/run-operator-tests.sh
+    docker_network: "host"
+    depends_on:
+      - k8sbuild
+      - manylinux-x86_64
+      - forge
+      - raycpubase(python=3.10)
+      - ray-core-build(python=3.10)
+      - ray-dashboard-build
+
+  - label: ":kubernetes: chaos {{matrix.workload}} under {{matrix.fault}}"
+    key: kuberay_tests
+    tags:
+      - core_python
+      - docker
+      - oss
+      - skip-on-premerge
+    instance_type: medium
+    commands:
+      - bash ci/k8s/run-chaos-test.sh {{matrix.fault}} {{matrix.workload}}
+    docker_network: "host"
+    matrix:
+      setup:
+        fault:
+          - "no_fault"
+          - "chaos_network_delay"
+          - "chaos_network_bandwidth"
+        workload:
+          - "test_potato_passer"
+          - "test_streaming_llm"
+          - "test_many_job_submissions"
+    depends_on:
+      - manylinux-x86_64
+      - forge
+      - raycpubase(python=3.10)
+      - ray-core-build(python=3.10)
+      - ray-dashboard-build

.buildkite/lint.rayci.yml

@@ -0,0 +1,52 @@
+group: lint
+steps:
+  - label: ":lint-roller: lint: {{matrix}}"
+    key: lint-small
+    tags:
+      - lint
+      - always
+    depends_on:
+      - forge
+    commands:
+      - ./ci/lint/lint.sh {{matrix}}
+    matrix:
+      - clang_format
+      - pre_commit
+      - semgrep_lint
+      - banned_words
+      - doc_readme
+      - dashboard_format
+      - copyright_format
+      - bazel_team
+      - bazel_buildifier
+      - pytest_format
+      - test_coverage
+      - documentation_style
+      - doc_no_new_rst
+
+  - label: ":lint-roller: pre-commit pydoclint"
+    key: pydoclint-small
+    tags:
+      - oss
+      - lint
+      - always
+    depends_on:
+      - forge
+    commands:
+      - ./ci/lint/lint.sh pre_commit_pydoclint
+
+  # Scope guard for the "docs-go" label: runs only when the label is present,
+  # and fails unless the PR is content-only (changes under doc/, excluding
+  # BUILD files). This is the check the label cannot turn off, so the label
+  # can skip doc/library tests on a content PR but never on a code, CI, or
+  # build change.
+  - label: ":lint-roller: lint: validate docs-go scope"
+    key: docs-go-scope
+    if: build.pull_request.labels includes "docs-go"
+    tags:
+      - oss
+      - always
+    depends_on:
+      - forge
+    commands:
+      - ./ci/lint/validate_docs_go_scope.sh

.buildkite/linux_aarch64.rayci.yml

@@ -0,0 +1,470 @@
+group: aarch64 tests
+sort_key: "~aarch64"
+steps:
+  # block on premerge and microcheck
+  - block: "Run Linux aarch64 tests"
+    if: build.env("BUILDKITE_PIPELINE_ID") == "0189942e-0876-4b8f-80a4-617f988ec59b" || build.env("BUILDKITE_PIPELINE_ID") == "018f4f1e-1b73-4906-9802-92422e3badaa"
+
+  - name: forge-aarch64
+    wanda: ci/docker/forge.aarch64.wanda.yaml
+    instance_type: builder-arm64
+
+  - name: manylinux-aarch64
+    wanda: ci/docker/manylinux.wanda.yaml
+    env_file: rayci.env
+    env:
+      HOSTTYPE: "aarch64"
+    instance_type: builder-arm64
+
+  - name: ray-java-build-aarch64
+    label: "wanda: java build (aarch64)"
+    wanda: ci/docker/ray-java.wanda.yaml
+    tags:
+      - release_wheels
+      - java
+    env_file: rayci.env
+    env:
+      ARCH_SUFFIX: "-aarch64"
+      HOSTTYPE: "aarch64"
+    instance_type: builder-arm64
+
+  - name: raycpubase-aarch64
+    label: "wanda: ray.py{{array.python}}.cpu.base (aarch64)"
+    tags:
+      - python_dependencies
+      - docker
+    wanda: docker/base-deps/cpu.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+    instance_type: builder-arm64
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      ARCH_SUFFIX: "-aarch64"
+
+  - name: raycpubaseextra-aarch64
+    label: "wanda: ray.py{{array.python}}.cpu.base-extra (aarch64)"
+    wanda: docker/base-extra/cpu.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+    instance_type: builder-arm64
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      IMAGE_TYPE: "ray"
+      ARCH_SUFFIX: "-aarch64"
+    depends_on: raycpubase-aarch64($)
+
+  - name: raycudabase-aarch64
+    label: "wanda: ray.py{{array.python}}.cu{{array.cuda}}.base (aarch64)"
+    tags:
+      - python_dependencies
+      - docker
+    wanda: docker/base-deps/cuda.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+      cuda:
+        - "11.7.1-cudnn8"
+        - "11.8.0-cudnn8"
+        - "12.1.1-cudnn8"
+        - "12.3.2-cudnn9"
+        - "12.4.1-cudnn"
+        - "12.5.1-cudnn"
+        - "12.6.3-cudnn"
+        - "12.8.1-cudnn"
+        - "12.9.1-cudnn"
+        - "13.0.0-cudnn"
+    instance_type: builder-arm64
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      CUDA_VERSION: "{{array.cuda}}"
+      ARCH_SUFFIX: "-aarch64"
+
+  - name: raycudabaseextra-aarch64
+    label: "wanda: ray.py{{array.python}}.cu{{array.cuda}}.base-extra (aarch64)"
+    wanda: docker/base-extra/cuda.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+      cuda:
+        - "11.7.1-cudnn8"
+        - "11.8.0-cudnn8"
+        - "12.1.1-cudnn8"
+        - "12.3.2-cudnn9"
+        - "12.4.1-cudnn"
+        - "12.5.1-cudnn"
+        - "12.6.3-cudnn"
+        - "12.8.1-cudnn"
+        - "12.9.1-cudnn"
+        - "13.0.0-cudnn"
+    instance_type: builder-arm64
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      CUDA_VERSION: "{{array.cuda}}"
+      IMAGE_TYPE: "ray"
+      ARCH_SUFFIX: "-aarch64"
+    depends_on: raycudabase-aarch64($)
+
+  # NOTE(andrew-anyscale): dashboard is architecture agnostic, but wanda pulls
+  # images for the architecture of the machine running the build. In the future,
+  # we can remove the arch suffix and pull from the x86_64 image to avoid
+  # duplicating this step.
+  - name: ray-dashboard-build-aarch64
+    label: "wanda: dashboard (aarch64)"
+    wanda: ci/docker/ray-dashboard.wanda.yaml
+    env_file: rayci.env
+    env:
+      ARCH_SUFFIX: "-aarch64"
+      HOSTTYPE: "aarch64"
+    tags: release_wheels
+    instance_type: builder-arm64
+
+  - name: ray-core-build-aarch64
+    label: "wanda: core binary parts py{{array.python}} (aarch64)"
+    wanda: ci/docker/ray-core.wanda.yaml
+    env_file: rayci.env
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+        - "3.14"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      ARCH_SUFFIX: "-aarch64"
+      HOSTTYPE: "aarch64"
+    tags: release_wheels
+    instance_type: builder-arm64
+
+  - name: ray-wheel-build-aarch64
+    label: "wanda: wheel py{{array.python}} (aarch64)"
+    wanda: ci/docker/ray-wheel.wanda.yaml
+    env_file: rayci.env
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+        - "3.14"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      ARCH_SUFFIX: "-aarch64"
+      HOSTTYPE: "aarch64"
+      JDK_SUFFIX: "-jdk"
+      RAY_JAVA_IMAGE: "cr.ray.io/rayproject/ray-java-build-aarch64"
+      RAY_DASHBOARD_IMAGE: "cr.ray.io/rayproject/ray-dashboard-aarch64"
+    tags:
+      - release_wheels
+      - linux_wheels
+    depends_on:
+      - ray-core-build-aarch64($)
+      - ray-java-build-aarch64
+      - ray-dashboard-build-aarch64
+    instance_type: builder-arm64
+
+  - label: ":arrow_up: upload: wheel py{{array.python}} (aarch64)"
+    key: linux_wheels_upload_aarch64
+    instance_type: small  # x86_64 instance since crane is currently only x86_64
+    commands:
+      - bazel run //ci/ray_ci/automation:extract_wanda_artifact --
+        --wanda-image-name=ray-wheel-py{{array.python}}-aarch64
+        --file-glob='*.whl'
+        --output-dir=.whl
+      - ./ci/build/copy_build_artifacts.sh wheel
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+        - "3.14"
+    depends_on:
+      - ray-wheel-build-aarch64($)
+      - forge
+    tags:
+      - release_wheels
+      - linux_wheels
+      - oss
+      - skip-on-premerge
+
+  - name: ray-cpp-core-build-aarch64
+    label: "wanda: cpp core (aarch64)"
+    wanda: ci/docker/ray-cpp-core.wanda.yaml
+    env_file: rayci.env
+    env:
+      ARCH_SUFFIX: "-aarch64"
+      HOSTTYPE: "aarch64"
+    tags:
+      - release_wheels
+      - oss
+    instance_type: builder-arm64
+
+  - name: ray-cpp-wheel-build-aarch64
+    label: "wanda: cpp wheel (aarch64)"
+    wanda: ci/docker/ray-cpp-wheel.wanda.yaml
+    env_file: rayci.env
+    env:
+      PYTHON_VERSION: "3.10"  # Used for upstream images; wheel is Python-agnostic
+      ARCH_SUFFIX: "-aarch64"
+      HOSTTYPE: "aarch64"
+    tags:
+      - release_wheels
+      - linux_wheels
+      - oss
+    depends_on:
+      - ray-core-build-aarch64(python=3.10)
+      - ray-cpp-core-build-aarch64
+      - ray-java-build-aarch64
+      - ray-dashboard-build-aarch64
+    instance_type: builder-arm64
+
+  - label: ":arrow_up: upload: cpp wheel (aarch64)"
+    key: linux_cpp_wheels_upload_aarch64
+    instance_type: small  # x86_64 instance since crane is currently only x86_64
+    commands:
+      - bazel run //ci/ray_ci/automation:extract_wanda_artifact --
+        --wanda-image-name=ray-cpp-wheel-aarch64
+        --file-glob='*.whl'
+        --output-dir=.whl
+      - ./ci/build/copy_build_artifacts.sh wheel
+    depends_on:
+      - ray-cpp-wheel-build-aarch64
+      - forge
+    tags:
+      - release_wheels
+      - linux_wheels
+      - oss
+      - skip-on-premerge
+
+  - name: ray-image-cpu-build-aarch64
+    label: "wanda: ray py{{array.python}} cpu (aarch64)"
+    wanda: ci/docker/ray-image-cpu.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+    env_file: rayci.env
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      ARCH_SUFFIX: "-aarch64"
+    tags:
+      - python_dependencies
+      - docker
+      - oss
+    depends_on:
+      - ray-wheel-build-aarch64($)
+      - raycpubase-aarch64($)
+    instance_type: builder-arm64
+
+  - name: ray-image-cuda-build-aarch64
+    label: "wanda: ray py{{array.python}} cu{{array.cuda}} (aarch64)"
+    wanda: ci/docker/ray-image-cuda.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+      cuda:
+        - "11.7.1-cudnn8"
+        - "11.8.0-cudnn8"
+        - "12.1.1-cudnn8"
+        - "12.3.2-cudnn9"
+        - "12.4.1-cudnn"
+        - "12.5.1-cudnn"
+        - "12.6.3-cudnn"
+        - "12.8.1-cudnn"
+        - "12.9.1-cudnn"
+        - "13.0.0-cudnn"
+    env_file: rayci.env
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      CUDA_VERSION: "{{array.cuda}}"
+      ARCH_SUFFIX: "-aarch64"
+    tags:
+      - python_dependencies
+      - docker
+      - oss
+    depends_on:
+      - ray-wheel-build-aarch64($)
+      - raycudabase-aarch64($)
+    instance_type: builder-arm64
+
+  - label: ":crane: publish: ray py{{array.python}} (aarch64)"
+    key: ray_images_push_aarch64
+    instance_type: small  # x86_64 instance since crane is currently only x86_64
+    commands:
+      - bazel run //.buildkite:copy_files -- --destination docker_login
+      - bazel run //ci/ray_ci/automation:push_ray_image --
+        --python-version {{array.python}}
+        --platform cpu
+        --platform cu11.7.1-cudnn8
+        --platform cu11.8.0-cudnn8
+        --platform cu12.1.1-cudnn8
+        --platform cu12.3.2-cudnn9
+        --platform cu12.4.1-cudnn
+        --platform cu12.5.1-cudnn
+        --platform cu12.6.3-cudnn
+        --platform cu12.8.1-cudnn
+        --platform cu12.9.1-cudnn
+        --platform cu13.0.0-cudnn
+        --image-type ray
+        --architecture aarch64
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+    depends_on:
+      - ray-image-cpu-build-aarch64($)
+      - ray-image-cuda-build-aarch64($)
+    tags:
+      - python_dependencies
+      - docker
+      - oss
+      - skip-on-premerge
+
+  - name: ray-extra-image-cpu-build-aarch64
+    label: "wanda: ray-extra py{{array.python}} cpu (aarch64)"
+    wanda: ci/docker/ray-extra-image-cpu.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+    env_file: rayci.env
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      ARCH_SUFFIX: "-aarch64"
+    tags:
+      - python_dependencies
+      - docker
+      - oss
+    depends_on:
+      - ray-wheel-build-aarch64($)
+      - raycpubaseextra-aarch64($)
+    instance_type: builder-arm64
+
+  - name: ray-extra-image-cuda-build-aarch64
+    label: "wanda: ray-extra py{{array.python}} cu{{array.cuda}} (aarch64)"
+    wanda: ci/docker/ray-extra-image-cuda.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+      cuda:
+        - "11.7.1-cudnn8"
+        - "11.8.0-cudnn8"
+        - "12.1.1-cudnn8"
+        - "12.3.2-cudnn9"
+        - "12.4.1-cudnn"
+        - "12.5.1-cudnn"
+        - "12.6.3-cudnn"
+        - "12.8.1-cudnn"
+        - "12.9.1-cudnn"
+        - "13.0.0-cudnn"
+    env_file: rayci.env
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      CUDA_VERSION: "{{array.cuda}}"
+      ARCH_SUFFIX: "-aarch64"
+    tags:
+      - python_dependencies
+      - docker
+      - oss
+    depends_on:
+      - ray-wheel-build-aarch64($)
+      - raycudabaseextra-aarch64($)
+    instance_type: builder-arm64
+
+  - label: ":crane: publish: ray-extra py{{array.python}} (aarch64)"
+    key: ray_extra_images_push_aarch64
+    instance_type: small
+    commands:
+      - bazel run //.buildkite:copy_files -- --destination docker_login
+      - bazel run //ci/ray_ci/automation:push_ray_image --
+        --python-version {{array.python}}
+        --platform cpu
+        --platform cu11.7.1-cudnn8
+        --platform cu11.8.0-cudnn8
+        --platform cu12.1.1-cudnn8
+        --platform cu12.3.2-cudnn9
+        --platform cu12.4.1-cudnn
+        --platform cu12.5.1-cudnn
+        --platform cu12.6.3-cudnn
+        --platform cu12.8.1-cudnn
+        --platform cu12.9.1-cudnn
+        --platform cu13.0.0-cudnn
+        --image-type ray-extra
+        --architecture aarch64
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+    depends_on:
+      - ray-extra-image-cpu-build-aarch64($)
+      - ray-extra-image-cuda-build-aarch64($)
+    tags:
+      - python_dependencies
+      - docker
+      - oss
+      - skip-on-premerge
+
+  - label: ":ray: core: wheel-aarch64 tests"
+    tags: linux_wheels
+    instance_type: medium-arm64
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... //doc/... core
+        --build-type wheel-aarch64
+        --build-name oss-ci-base_build-aarch64
+        --parallelism-per-worker 3
+        --only-tags post_wheel_build
+        --test-env=RAY_CI_POST_WHEEL_TESTS=True
+        --python-version 3.10
+    depends_on:
+      - manylinux-aarch64
+      - oss-ci-base_build-aarch64
+      - forge-aarch64
+      - ray-wheel-build-aarch64(python=3.10)
+    job_env: forge-aarch64
+
+  - label: ":ray-serve: serve: wheel-aarch64 tests"
+    tags: linux_wheels
+    instance_type: medium-arm64
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/serve/... //doc/... serve
+        --build-type wheel-aarch64
+        --build-name oss-ci-base_build-aarch64
+        --parallelism-per-worker 3
+        --only-tags post_wheel_build
+        --test-env=RAY_CI_POST_WHEEL_TESTS=True
+        --python-version 3.10
+    depends_on:
+      - manylinux-aarch64
+      - oss-ci-base_build-aarch64
+      - forge-aarch64
+      - ray-wheel-build-aarch64(python=3.10)
+    job_env: forge-aarch64

.buildkite/llm.rayci.yml

@@ -0,0 +1,88 @@
+group: llm tests
+depends_on:
+  - forge
+  - ray-core-build(*)
+  - ray-dashboard-build
+steps:
+  - name: llmbuild
+    wanda: ci/docker/llm.build.wanda.yaml
+    depends_on:
+      - oss-ci-base_build-multipy(python=3.12)
+    env:
+      PYTHON: "3.12"
+      BASE_TYPE: "build"
+      BUILD_VARIANT: "build"
+      RAY_CUDA_CODE: "cpu"
+    tags: cibase
+
+  - name: llmgpubuild
+    wanda: ci/docker/llm.build.wanda.yaml
+    depends_on:
+      - oss-ci-base_cu130-multipy(python=3.12)
+    env:
+      PYTHON: "3.12"
+      BASE_TYPE: "cu130"
+      BUILD_VARIANT: "gpubuild"
+      RAY_CUDA_CODE: "cu130"
+    tags: cibase
+
+  # Dedicated image for the custom-vllm-model docs example: the LLM GPU image
+  # plus a vllm plugin for model with custom architecture.
+  - name: custom-vllm-plugin-gpubuild
+    wanda: ci/docker/custom-vllm-plugin.build.wanda.yaml
+    depends_on: llmgpubuild
+    tags: cibase
+
+  - label: "llm cpu tests"
+    if: '!(build.pull_request.labels includes "docs-go")'
+    key: "llm-cpu-tests"
+    tags:
+      - llm
+      - cpu
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/llm/... //doc/... llm
+        --python-version 3.12 --build-name llmbuild
+        --except-tags gpu
+    depends_on: llmbuild
+
+  - label: "llm gpu tests"
+    if: '!(build.pull_request.labels includes "docs-go")'
+    key: "llm-gpu-tests"
+    tags:
+      - llm
+      - gpu
+    instance_type: g6-large
+    commands:
+      - RAYCI_DISABLE_TEST_DB=1 bazel run //ci/ray_ci:test_in_docker -- //python/ray/llm/... //doc/... llm
+        --python-version 3.12 --build-name llmgpubuild --only-tags gpu
+        --except-tags multi_gpu_4,custom_vllm_plugin
+    depends_on: llmgpubuild
+
+  - label: "llm gpu tests (4 GPUs)"
+    if: '!(build.pull_request.labels includes "docs-go")'
+    key: "llm-gpu-tests-4gpu"
+    tags:
+      - llm
+      - gpu
+    instance_type: gpu-large
+    commands:
+      - RAYCI_DISABLE_TEST_DB=1 bazel run //ci/ray_ci:test_in_docker -- //doc/... llm
+        --python-version 3.12 --build-name llmgpubuild
+        --only-tags multi_gpu_4
+        --gpus 4
+    depends_on: llmgpubuild
+
+  # Custom vLLM model docs example: runs on the dedicated image that has the
+  # qwen3_reward_plugin baked in.
+  - label: "llm custom vllm plugin gpu test"
+    key: "llm-custom-vllm-plugin-gpu-test"
+    tags:
+      - llm
+      - gpu
+    instance_type: g6-large
+    commands:
+      - RAYCI_DISABLE_TEST_DB=1 bazel run //ci/ray_ci:test_in_docker -- //doc/... llm
+        --python-version 3.12 --build-name custom-vllm-plugin-gpubuild
+        --only-tags custom_vllm_plugin
+    depends_on: custom-vllm-plugin-gpubuild

.buildkite/macos.rayci.yml

@@ -0,0 +1 @@
+macos/macos.rayci.yml

.buildkite/macos/always.rules.test.txt

@@ -0,0 +1 @@
+../always.rules.test.txt

.buildkite/macos/always.rules.txt

@@ -0,0 +1 @@
+../always.rules.txt

.buildkite/macos/config.yml

@@ -0,0 +1,18 @@
+name: ray-postmerge-macos
+artifacts_bucket: ray-ci-artifact-branch-public
+ci_temp: s3://ray-ci-artifact-branch-public/ci-temp/
+ci_work_repo: 029272617770.dkr.ecr.us-west-2.amazonaws.com/rayproject/citemp
+forge_prefix: cr.ray.io/rayproject/
+builder_queues:
+  builder: builder_queue_branch
+runner_queues:
+  macos: macos-branch
+  macos-arm64: macos-branch-arm64
+buildkite_dirs:
+  - .buildkite/macos
+env:
+  BUILDKITE_BAZEL_CACHE_URL: https://bazel-cache-dev.s3.us-west-2.amazonaws.com
+hook_env_keys:
+  - RAYCI_CHECKOUT_DIR
+skip_tags:
+  - disabled

.buildkite/macos/macos.rayci.yml

@@ -0,0 +1,123 @@
+group: macos tests
+sort_key: "~macos"
+steps:
+  - label: ":ray: core: :mac: smoke test"
+    if: build.env("BUILDKITE_PIPELINE_ID") == "0189942e-0876-4b8f-80a4-617f988ec59b" || build.env("BUILDKITE_PIPELINE_ID") == "018f4f1e-1b73-4906-9802-92422e3badaa"
+    tags:
+      - core_cpp
+      - macos_wheels
+    job_env: MACOS
+    instance_type: macos-arm64
+    commands:
+      - ./ci/ray_ci/macos/macos_ci.sh run_smoke_test
+
+  # block full test suite on premerge and microcheck
+  - block: "run macos tests"
+    key: block-macos-tests
+    if: build.env("BUILDKITE_PIPELINE_ID") == "0189942e-0876-4b8f-80a4-617f988ec59b" || build.env("BUILDKITE_PIPELINE_ID") == "018f4f1e-1b73-4906-9802-92422e3badaa"
+    depends_on: []
+
+  - label: ":tapioca: build: :mac: wheels and jars (aarch64)"
+    key: macos_wheels_arm64
+    if: build.env("BUILDKITE_PIPELINE_ID") != "0189e759-8c96-4302-b6b5-b4274406bf89"
+    tags:
+      - macos_wheels
+      - python_dependencies
+      - release_wheels
+    job_env: MACOS
+    instance_type: macos-arm64
+    commands:
+      - bash ci/ray_ci/macos/macos_ci_build.sh
+    depends_on: block-macos-tests
+
+  # test
+  - label: ":ray: core: :mac: small & client tests"
+    if: build.env("BUILDKITE_PIPELINE_ID") != "0189e759-8c96-4302-b6b5-b4274406bf89"
+    tags:
+      - core_cpp
+      - core_python
+      - macos_wheels
+    job_env: MACOS
+    instance_type: macos-arm64
+    commands:
+      - ./ci/ray_ci/macos/macos_ci.sh run_small_test
+    depends_on: block-macos-tests
+
+  - label: ":ray: core: :mac: medium tests (shard 1)"
+    if: build.env("BUILDKITE_PIPELINE_ID") != "0189e759-8c96-4302-b6b5-b4274406bf89"
+    tags:
+      - core_cpp
+      - core_python
+      - macos_wheels
+    job_env: MACOS
+    instance_type: macos-arm64
+    commands:
+      - ./ci/ray_ci/macos/macos_ci.sh run_medium_test_shard_0
+    depends_on: block-macos-tests
+
+  - label: ":ray: core: :mac: medium tests (shard 2)"
+    if: build.env("BUILDKITE_PIPELINE_ID") != "0189e759-8c96-4302-b6b5-b4274406bf89"
+    tags:
+      - core_cpp
+      - core_python
+      - macos_wheels
+    job_env: MACOS
+    instance_type: macos-arm64
+    commands:
+      - ./ci/ray_ci/macos/macos_ci.sh run_medium_test_shard_1
+    depends_on: block-macos-tests
+
+  - label: ":ray: core: :mac: large tests"
+    if: build.env("BUILDKITE_PIPELINE_ID") != "0189e759-8c96-4302-b6b5-b4274406bf89"
+    tags:
+      - core_cpp
+      - core_python
+      - macos_wheels
+      - oss
+    job_env: MACOS
+    instance_type: macos-arm64
+    parallelism: 3
+    commands:
+      - ./ci/ray_ci/macos/macos_ci.sh run_large_test
+    depends_on: block-macos-tests
+
+  - label: ":ray: core: :mac: core and dashboard tests"
+    if: build.env("BUILDKITE_PIPELINE_ID") != "0189e759-8c96-4302-b6b5-b4274406bf89"
+    tags:
+      - core_cpp
+      - core_python
+      - dashboard
+      - macos_wheels
+    job_env: MACOS
+    instance_type: macos-arm64
+    commands:
+      - ./ci/ray_ci/macos/macos_ci.sh run_core_dashboard_test
+    depends_on: block-macos-tests
+
+  - label: ":ray: core: :mac: core c++ and java tests"
+    if: build.env("BUILDKITE_PIPELINE_ID") != "0189e759-8c96-4302-b6b5-b4274406bf89"
+    tags:
+      - cpp
+      - java
+      - macos_wheels
+    job_env: MACOS
+    instance_type: macos-arm64
+    commands:
+      - RAY_INSTALL_JAVA=0 ./ci/ray_ci/macos/macos_ci.sh run_ray_cpp
+    depends_on: block-macos-tests
+
+  - label: ":ray: core: :mac: flaky tests"
+    key: macos_flaky_tests
+    if: build.env("BUILDKITE_PIPELINE_ID") != "0189e759-8c96-4302-b6b5-b4274406bf89"
+    tags:
+      - core_cpp
+      - core_python
+      - macos_wheels
+      - flaky
+      - skip_on_premerge
+    job_env: MACOS
+    instance_type: macos-arm64
+    soft_fail: true
+    commands:
+      - ./ci/ray_ci/macos/macos_ci.sh run_flaky_tests
+    depends_on: block-macos-tests

.buildkite/macos/test.rules.test.txt

@@ -0,0 +1 @@
+../test.rules.test.txt

.buildkite/macos/test.rules.txt

@@ -0,0 +1 @@
+../test.rules.txt

.buildkite/ml.rayci.yml

@@ -0,0 +1,391 @@
+group: ml tests
+depends_on:
+  - forge
+  - ray-core-build(*)
+  - ray-dashboard-build
+steps:
+  # builds
+  - name: minbuild-ml
+    label: "wanda: minbuild-ml-py{{array.python}}"
+    wanda: ci/docker/min.build.wanda.yaml
+    depends_on: oss-ci-base_test-multipy($)
+    array:
+      python:
+        - "3.10"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      EXTRA_DEPENDENCY: ml
+    tags: cibase
+
+  - name: mlbuild-multipy
+    label: "wanda: mlbuild-py{{array.python}}"
+    wanda: ci/docker/ml.build.wanda.yaml
+    depends_on: oss-ci-base_ml-multipy($)
+    env:
+      PYTHON: "{{array.python}}"
+      BASE_TYPE: "ml"
+      IMAGE_TYPE: "build"
+      RAYCI_IS_GPU_BUILD: "false"
+    array:
+      python:
+        - "3.10"
+        - "3.12"
+    tags: cibase
+
+  - name: mltorchft
+    label: "wanda: mltorchft-py3.10"
+    wanda: ci/docker/ml.build.wanda.yaml
+    depends_on: oss-ci-base_ml-multipy(python=3.10)
+    env:
+      PYTHON: "3.10"
+      BASE_TYPE: "ml"
+      IMAGE_TYPE: "torchft"
+      RAYCI_IS_GPU_BUILD: "false"
+    tags: cibase
+
+  - name: mllightning1gpubuild
+    wanda: ci/docker/ml.build.wanda.yaml
+    env:
+      PYTHON: "3.10"
+      BASE_TYPE: "gpu"
+      IMAGE_TYPE: "lightning1gpubuild"
+      RAYCI_IS_GPU_BUILD: "true"
+    tags: cibase
+    depends_on: oss-ci-base_gpu-multipy(python=3.10)
+
+  - name: mlgpubuild-multipy
+    label: "wanda: mlgpubuild-py{{array.python}}"
+    wanda: ci/docker/ml.build.wanda.yaml
+    depends_on: oss-ci-base_gpu-multipy($)
+    env:
+      PYTHON: "{{array.python}}"
+      BASE_TYPE: "gpu"
+      IMAGE_TYPE: "gpubuild"
+      RAYCI_IS_GPU_BUILD: "true"
+    array:
+      python:
+        - "3.10"
+        - "3.12"
+    tags: cibase
+
+  # tests
+  - label: ":train: ml: train v1 tests"
+    tags: train
+    instance_type: large
+    parallelism: 2
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/train/... ml
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 3
+        --except-tags gpu,minimal,tune,doctest,needs_credentials,train_v2,train_v2_gpu,data_integration
+        --python-version 3.10 --build-name mlbuild-py3.10
+    depends_on: [ "mlbuild-multipy(python=3.10)", "forge" ]
+
+  - label: ":bullettrain_front: ml: train v2 tests"
+    tags: train
+    instance_type: large
+    parallelism: 2
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/train/... ml
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 3
+        --python-version 3.10 --build-name mlbuild-py3.10
+        --only-tags train_v2
+        --except-tags needs_credentials,data_integration,torchft
+    depends_on: [ "mlbuild-multipy(python=3.10)", "forge" ]
+
+  - label: ":bullettrain_front: ml: train v2 torch trainer tests (torchft image)"
+    tags: train
+    instance_type: small
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/train/... ml
+        --python-version 3.10 --build-name mltorchft-py3.10
+        --only-tags torchft
+        --except-tags needs_credentials,data_integration
+    depends_on: [ "mltorchft", "forge" ]
+
+  - label: ":bullettrain_front: ml: train v2 gpu tests"
+    tags:
+      - train_gpu
+      - gpu
+    instance_type: gpu-large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/train/... //doc/... ml
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 2
+        --build-name mlgpubuild-py3.10 --python-version 3.10
+        --only-tags train_v2_gpu
+        --except-tags data_integration
+    depends_on: [ "mlgpubuild-multipy(python=3.10)", "forge" ]
+
+  - label: ":bullettrain_front: :python: ml: train v2 {{array.python}} tests ({{array.worker_id}})"
+    key: ml_train_v2_python_tests
+    if: build.pull_request.labels includes "continuous-build" || pipeline.id == "0189e759-8c96-4302-b6b5-b4274406bf89" || pipeline.id == "018f4f1e-1b73-4906-9802-92422e3badaa"
+    tags:
+      - train
+      - tune
+      - ml
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/train/... ml
+        --workers 2 --worker-id {{array.worker_id}} --parallelism-per-worker 3
+        --python-version {{array.python}} --build-name mlbuild-py{{array.python}}
+        --only-tags train_v2
+        --except-tags needs_credentials,torchft
+    depends_on: [ "mlbuild-multipy($)", "forge" ]
+    array:
+      python: ["3.12"]
+      worker_id: ["0", "1"]
+
+  - label: ":train: ml: train v1 gpu tests"
+    tags:
+      - train_gpu
+      - gpu
+    instance_type: gpu-large
+    parallelism: 2
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/train/... //python/ray/air/... //doc/... ml
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 2
+        --build-name mlgpubuild-py3.10 --python-version 3.10
+        --only-tags gpu
+        --except-tags data_integration
+    depends_on: [ "mlgpubuild-multipy(python=3.10)", "forge" ]
+
+  - label: ":train: ml: data integration tests"
+    tags:
+      - data
+      - train
+    instance_type: gpu
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/train/... ml
+        --python-version 3.10 --build-name mlgpubuild-py3.10
+        --only-tags data_integration
+    depends_on: [ "mlgpubuild-multipy(python=3.10)", "forge" ]
+
+  - label: ":bullettrain_front: :python: ml: train v2 gpu {{array.python}} tests ({{array.worker_id}})"
+    key: ml_train_v2_gpu_python_tests
+    if: build.pull_request.labels includes "continuous-build" || pipeline.id == "0189e759-8c96-4302-b6b5-b4274406bf89" || pipeline.id == "018f4f1e-1b73-4906-9802-92422e3badaa"
+    tags:
+      - train_gpu
+      - gpu
+    instance_type: gpu-large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/train/... //python/ray/air/... //doc/... ml
+        --workers 2 --worker-id {{array.worker_id}} --parallelism-per-worker 2
+        --python-version {{array.python}}
+        --build-name mlgpubuild-py{{array.python}}
+        --only-tags train_v2_gpu
+        --except-tags doctest,data_integration
+    depends_on: [ "mlgpubuild-multipy($)", "forge" ]
+    array:
+      python: ["3.12"]
+      worker_id: ["0", "1"]
+
+  - label: ":train: ml: train authentication tests"
+    tags:
+      - train
+      - branch
+      - skip-on-premerge
+      - oss
+    instance_type: medium
+    commands:
+      - $(python ci/env/setup_credentials.py)
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/train/... ml
+        --parallelism-per-worker 3
+        --python-version 3.10 --build-name mlbuild-py3.10
+        --only-tags needs_credentials
+        --test-env=WANDB_API_KEY --test-env=COMET_API_KEY
+    depends_on: [ "mlbuild-multipy(python=3.10)", "forge" ]
+
+  - label: ":train: ml: tune tests"
+    tags: tune
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tune/... ml
+        --parallelism-per-worker 3
+        --python-version 3.10 --build-name mlbuild-py3.10
+        --except-tags doctest,soft_imports,rllib
+    depends_on: [ "mlbuild-multipy(python=3.10)", "forge" ]
+
+  - label: ":bullettrain_front: :python: ml: tune {{array.python}} tests"
+    key: ml_tune_python_tests
+    if: build.pull_request.labels includes "continuous-build" || pipeline.id == "0189e759-8c96-4302-b6b5-b4274406bf89" || pipeline.id == "018f4f1e-1b73-4906-9802-92422e3badaa"
+    tags: tune
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tune/... ml
+        --parallelism-per-worker 3
+        --python-version {{array.python}} --build-name mlbuild-py{{array.python}}
+        --except-tags doctest,soft_imports,rllib
+    depends_on: [ "mlbuild-multipy($)", "forge" ]
+    array:
+      python: ["3.12"]
+
+  - label: ":train: ml: tune soft import tests"
+    tags: tune
+    instance_type: small
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tune/... ml
+        --only-tags soft_imports
+        --build-name oss-ci-base_build-py3.10 --python-version 3.10
+    depends_on: [ "oss-ci-base_build-multipy(python=3.10)", "forge" ]
+
+  - label: ":train: ml: air tests"
+    tags: ml
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/air/... ml
+        --parallelism-per-worker 3
+        --python-version 3.10 --build-name mlbuild-py3.10
+        --except-tags gpu,doctest
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/data/... ml
+        --python-version 3.10 --build-name mlbuild-py3.10
+        --parallelism-per-worker 3
+        --only-tags ray_air
+        --skip-ray-installation
+    depends_on: [ "mlbuild-multipy(python=3.10)", "forge" ]
+
+  - label: ":train: ml: train+tune tests"
+    tags: train
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/train/... ml
+        --parallelism-per-worker 3
+        --python-version 3.10 --build-name mlbuild-py3.10
+        --only-tags tune
+        --except-tags ray_air,gpu,doctest,needs_credentials
+    depends_on: [ "mlbuild-multipy(python=3.10)", "forge" ]
+
+  - label: ":train: ml: rllib+tune tests"
+    tags:
+      - tune
+      - rllib
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tune/... ml
+        --python-version 3.10 --build-name mlbuild-py3.10
+        --parallelism-per-worker 3
+        --only-tags rllib
+        --except-tags gpu
+    depends_on: [ "mlbuild-multipy(python=3.10)", "forge" ]
+
+  - label: ":train: ml: release tests"
+    tags:
+      - ml
+      - core_python
+      - release_tests
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //release/... ml
+        --python-version 3.10 --build-name mlbuild-py3.10
+        --parallelism-per-worker 3
+    depends_on: [ "mlbuild-multipy(python=3.10)", "forge" ]
+
+  - label: ":train: ml: train minimal"
+    tags:
+      - train
+      - min_build
+    instance_type: small
+    commands:
+      - python ./ci/env/check_minimal_install.py
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/train/... ml
+        --parallelism-per-worker 2
+        --build-name minbuild-ml-py3.10 --python-version 3.10
+        --only-tags minimal
+    depends_on: [ "minbuild-ml(python=3.10)", "forge" ]
+
+  - label: ":train: ml: doc tests"
+    if: '!(build.pull_request.labels includes "docs-go")'
+    tags:
+      - train
+      - tune
+      - doc
+    instance_type: large
+    parallelism: 2
+    commands:
+      # doc tests
+      - bazel run //ci/ray_ci:test_in_docker -- python/ray/... //doc/... ml
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}"
+        --python-version 3.10 --build-name mlbuild-py3.10
+        --only-tags doctest
+        --except-tags gpu
+        --parallelism-per-worker 3
+      # doc examples
+      - bazel run //ci/ray_ci:test_in_docker -- //doc/... ml
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}"
+        --python-version 3.10 --build-name mlbuild-py3.10
+        --except-tags gpu,post_wheel_build,doctest,highly_parallel
+        --parallelism-per-worker 3
+        --skip-ray-installation
+    depends_on: [ "mlbuild-multipy(python=3.10)", "forge" ]
+
+  - label: ":train: ml: lightning 1.x compatibility tests"
+    tags:
+      - train_gpu
+      - gpu
+    instance_type: gpu-large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/train/... ml
+        --build-name mllightning1gpubuild-py3.10 --python-version 3.10
+        --only-tags ptl_v1
+    depends_on: [ "mllightning1gpubuild", "forge" ]
+
+  - label: ":train: ml: flaky tests"
+    key: ml_flaky_tests
+    tags:
+      - train
+      - flaky
+      - skip-on-premerge
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //... ml --run-flaky-tests
+        --python-version 3.10 --build-name mlbuild-py3.10
+        --parallelism-per-worker 2
+        --except-tags gpu,needs_credentials,train_v2_gpu,data_integration,torchft
+    depends_on: [ "mlbuild-multipy(python=3.10)", "forge" ]
+    soft_fail: true
+
+  - label: ":train: ml: flaky authentication tests"
+    tags:
+      - train
+      - branch
+      - skip-on-premerge
+      - oss
+    instance_type: medium
+    commands:
+      - $(python ci/env/setup_credentials.py)
+      - bazel run //ci/ray_ci:test_in_docker -- //... ml --run-flaky-tests
+        --python-version 3.10 --build-name mlbuild-py3.10
+        --parallelism-per-worker 3
+        --only-tags needs_credentials
+        --test-env=WANDB_API_KEY --test-env=COMET_API_KEY
+    depends_on: [ "mlbuild-multipy(python=3.10)", "forge" ]
+    soft_fail: true
+
+  - label: ":bullettrain_front: ml: train v2 torch trainer flaky tests (torchft image)"
+    key: ml_torch_trainer_flaky_tests
+    tags:
+      - train
+      - flaky
+      - skip-on-premerge
+    instance_type: small
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/train/... ml --run-flaky-tests
+        --python-version 3.10 --build-name mltorchft-py3.10
+        --only-tags torchft
+        --except-tags needs_credentials,data_integration
+    depends_on: [ "mltorchft", "forge" ]
+    soft_fail: true
+
+  - label: ":train: ml: train gpu flaky tests"
+    key: ml_flaky_gpu_tests
+    tags:
+      - train
+      - skip-on-premerge
+      - gpu
+    instance_type: gpu-large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //... ml --run-flaky-tests
+        --parallelism-per-worker 2
+        --python-version 3.10 --build-name mlgpubuild-py3.10
+        --only-tags gpu,train_v2_gpu
+        --except-tags data_integration
+    depends_on: [ "mlgpubuild-multipy(python=3.10)", "forge" ]
+    soft_fail: true

.buildkite/others.rayci.yml

@@ -0,0 +1,85 @@
+group: others
+depends_on:
+  - forge
+steps:
+  # docs
+  - name: doctestbuild
+    wanda: ci/docker/doctest.build.wanda.yaml
+    depends_on: oss-ci-base_build-multipy(python=3.10)
+    env:
+      PYTHON: "3.10"
+    tags: cibase
+
+  - label: doc tests
+    tags: python
+    instance_type: large
+    commands:
+      # Disable test DB to avoid any hidden failures going forward.
+      - RAYCI_DISABLE_TEST_DB=1 bazel run //ci/ray_ci:test_in_docker -- //python/ray/... //doc/... none
+        --build-name doctestbuild
+        --only-tags doctest
+        --except-tags gpu
+        --parallelism-per-worker 3
+        --python-version 3.10
+    depends_on:
+      - doctestbuild
+      - ray-core-build(python=3.10)
+      - ray-dashboard-build
+
+  # java
+  - label: ":java: java tests"
+    tags: java
+    instance_type: medium
+    commands:
+      # Java tests need the C++ API for multi-langauge worker tests.
+      - bazel run //ci/ray_ci:test_in_docker -- //... core --build-type multi-lang --build-only
+        --python-version 3.10 --build-name corebuild-py3.10
+      - docker run -i --rm --volume /tmp/artifacts:/artifact-mount --shm-size=2.5gb
+        "$${RAYCI_WORK_REPO}":"$${RAYCI_BUILD_ID}"-corebuild-py3.10 /bin/bash -iecuo pipefail
+        "./java/test.sh"
+    depends_on: corebuild-multipy(python=3.10)
+
+  # bot
+  - label: ":robot_face: CI weekly green metric"
+    tags:
+      - skip-on-premerge
+      - oss
+    if: build.branch == "master"
+    instance_type: small
+    commands:
+      - bazel run //ci/ray_ci/automation:weekly_green_metric -- --production
+
+  - label: ":robot_face: {{matrix}} microcheck test coverage"
+    tags:
+      - skip-on-premerge
+      - oss
+    if: build.branch == "master"
+    instance_type: small
+    commands:
+      - bazel run //ci/ray_ci/automation:determine_microcheck_tests -- {{matrix}} 100 --test-prefix linux:__ --production
+      # we use master branch to determine microcheck tests for darwin and windows, because darwin and windows tests do not run on premerge branches
+      - bazel run //ci/ray_ci/automation:determine_microcheck_tests -- {{matrix}} 100 --test-prefix darwin:__ --consider-master-branch --production
+      - bazel run //ci/ray_ci/automation:determine_microcheck_tests -- {{matrix}} 100 --test-prefix windows:__ --consider-master-branch --production
+    matrix:
+      - "core"
+      - "serve"
+      - "data"
+      - "ml"
+      - "rllib"
+      - "ci"
+
+  - name: fossa-base
+    wanda: ci/docker/fossa.wanda.yaml
+    depends_on: forge
+
+  - label: "fossa analyze"
+    key: fossa-analyze
+    tags:
+      - skip-on-premerge
+      - fossa
+      - oss
+    instance_type: small
+    commands:
+      - bash ci/fossa/analyze.sh
+    depends_on: fossa-base
+    job_env: fossa-base

.buildkite/release-automation/check-commit-hash.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+set -euo pipefail
+
+set -x
+
+if [[ "${BUILDKITE_COMMIT}" != "$(git rev-parse HEAD)" ]]; then
+    echo "Commit hash mismatch"
+    exit 1
+else echo "Commit hash matches"; fi

.buildkite/release-automation/config.yml

@@ -0,0 +1,26 @@
+name: ray-release-automation
+artifacts_bucket: ray-ci-artifact-pr-public
+ci_temp: s3://ray-ci-artifact-pr-public/ci-temp/
+ci_work_repo: 029272617770.dkr.ecr.us-west-2.amazonaws.com/rayproject/citemp
+forge_prefix: cr.ray.io/rayproject/
+builder_queues:
+  builder: builder_queue_pr
+  builder-arm64: builder_queue_arm64_pr
+  builder-windows: builder_queue_windows_pr
+runner_queues:
+  default: runner_queue_small_pr
+  medium-arm64: runner_queue_arm64_medium_pr
+  macos: macos
+  macos-arm64: macos-pr-arm64
+  windows: windows_queue_pr
+  small_branch: runner_queue_small_branch
+builder_priority: 5
+runner_priority: 5
+buildkite_dirs:
+  - .buildkite/release-automation
+env:
+  BUILDKITE_BAZEL_CACHE_URL: https://bazel-cache-dev.s3.us-west-2.amazonaws.com
+  RAYCI_SKIP_UPLOAD: "true"
+skip_tags:
+  - disabled
+allow_trigger_step: true

.buildkite/release-automation/forge.rayci.yml

@@ -0,0 +1,8 @@
+group: forge
+steps:
+  - name: forge
+    wanda: .buildkite/release-automation/forge_x86_64.wanda.yaml
+
+  - name: forge-arm64
+    wanda: .buildkite/release-automation/forge_arm64.wanda.yaml
+    instance_type: builder-arm64

.buildkite/release-automation/forge_arm64.Dockerfile

@@ -0,0 +1,55 @@
+# syntax=docker/dockerfile:1.3-labs
+
+FROM ubuntu:22.04
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN <<EOF
+#!/bin/bash
+
+set -euo pipefail
+
+apt-get update
+apt-get upgrade -y
+apt-get install -y curl zip clang-14
+
+ln -s /usr/bin/clang-14 /usr/bin/clang
+
+# Install miniforge3
+curl -fsSL https://github.com/conda-forge/miniforge/releases/download/25.3.0-1/Miniforge3-25.3.0-1-Linux-aarch64.sh > /tmp/miniforge3.sh
+bash /tmp/miniforge3.sh -b -u -p /usr/local/bin/miniforge3
+rm /tmp/miniforge3.sh
+/usr/local/bin/miniforge3/bin/conda init bash
+
+# Install Bazelisk
+curl -fsSL https://github.com/bazelbuild/bazelisk/releases/download/v1.19.0/bazelisk-linux-arm64 --output /usr/local/bin/bazelisk
+chmod +x /usr/local/bin/bazelisk
+
+ln -s /usr/local/bin/bazelisk /usr/local/bin/bazel
+
+# Install uv
+curl -fsSL https://astral.sh/uv/install.sh | env UV_UNMANAGED_INSTALL="/usr/local/bin" sh
+
+mkdir -p /usr/local/python
+# Install Python using uv
+UV_PYTHON_VERSION=3.10
+uv python install --install-dir /usr/local/python "$UV_PYTHON_VERSION"
+
+export UV_PYTHON_INSTALL_DIR=/usr/local/python
+# Make Python from uv the default by creating symlinks
+UV_PYTHON_BIN="$(uv python find --no-project "$UV_PYTHON_VERSION")"
+echo "uv python binary location: $UV_PYTHON_BIN"
+ln -s "$UV_PYTHON_BIN" "/usr/local/bin/python${UV_PYTHON_VERSION}"
+ln -s "$UV_PYTHON_BIN" /usr/local/bin/python3
+ln -s "$UV_PYTHON_BIN" /usr/local/bin/python
+
+# As a convention, we pin all python packages to a specific version. This
+# is to to make sure we can control version upgrades through code changes.
+uv pip install --system pip==25.2 cffi==1.16.0
+
+EOF
+
+ENV CC=clang
+ENV CXX=clang++-14
+
+CMD ["echo", "ray release-automation forge"]

.buildkite/release-automation/forge_arm64.wanda.yaml

@@ -0,0 +1,4 @@
+name: "forge-arm64"
+froms:
+  - ubuntu:22.04
+dockerfile: .buildkite/release-automation/forge_arm64.Dockerfile

.buildkite/release-automation/forge_x86_64.Dockerfile

@@ -0,0 +1,66 @@
+# syntax=docker/dockerfile:1.3-labs
+
+FROM ubuntu:22.04
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN <<EOF
+#!/bin/bash
+
+set -euo pipefail
+
+apt-get update
+apt-get upgrade -y
+apt-get install -y curl zip clang-14 git
+
+# Needs to be synchronized to the host group id as we map /var/run/docker.sock
+# into the container.
+addgroup --gid 993 docker
+addgroup --gid 992 docker1 # docker group on buildkite AMI as of 2025-06-07
+
+ln -s /usr/bin/clang-14 /usr/bin/clang
+
+# Install miniforge3
+curl -fsSL https://github.com/conda-forge/miniforge/releases/download/25.3.0-1/Miniforge3-25.3.0-1-Linux-x86_64.sh > /tmp/miniforge3.sh
+bash /tmp/miniforge3.sh -b -u -p /usr/local/bin/miniforge3
+rm /tmp/miniforge3.sh
+/usr/local/bin/miniforge3/bin/conda init bash
+
+# Install Bazelisk
+curl -fsSL https://github.com/bazelbuild/bazelisk/releases/download/v1.19.0/bazelisk-linux-amd64 --output /usr/local/bin/bazelisk
+chmod +x /usr/local/bin/bazelisk
+
+ln -s /usr/local/bin/bazelisk /usr/local/bin/bazel
+
+# Install uv
+curl -fsSL https://astral.sh/uv/install.sh | env UV_UNMANAGED_INSTALL="/usr/local/bin" sh
+
+mkdir -p /usr/local/python
+# Install Python using uv
+UV_PYTHON_VERSION=3.10
+uv python install --install-dir /usr/local/python "$UV_PYTHON_VERSION"
+
+export UV_PYTHON_INSTALL_DIR=/usr/local/python
+# Make Python from uv the default by creating symlinks
+UV_PYTHON_BIN="$(uv python find --no-project "$UV_PYTHON_VERSION")"
+echo "uv python binary location: $UV_PYTHON_BIN"
+ln -s "$UV_PYTHON_BIN" "/usr/local/bin/python${UV_PYTHON_VERSION}"
+ln -s "$UV_PYTHON_BIN" /usr/local/bin/python3
+ln -s "$UV_PYTHON_BIN" /usr/local/bin/python
+
+# As a convention, we pin all python packages to a specific version. This
+# is to to make sure we can control version upgrades through code changes.
+uv pip install --system pip==25.2 cffi==1.16.0
+
+# A non-root user. Use 2000, which is the same as our buildkite agent VM uses.
+adduser --home /home/forge --uid 2000 forge --gid 100
+usermod -a -G docker forge
+usermod -a -G docker1 forge
+
+EOF
+
+USER forge
+ENV CC=clang
+ENV CXX=clang++-14
+
+CMD ["echo", "ray release-automation forge"]

.buildkite/release-automation/forge_x86_64.wanda.yaml

@@ -0,0 +1,4 @@
+name: "forge"
+froms:
+  - ubuntu:22.04
+dockerfile: .buildkite/release-automation/forge_x86_64.Dockerfile

.buildkite/release-automation/pre_release.rayci.yml

@@ -0,0 +1,137 @@
+group: Pre-release checks
+depends_on:
+  - forge
+steps:
+  - block: "Run pre-release checks"
+    if: build.env("RAY_VERSION") != null
+    key: block-pre-release-checks
+    depends_on: []
+
+  - label: "Check release blockers"
+    key: check-release-blockers
+    instance_type: small_branch
+    commands:
+      - bazel run //ci/ray_ci/automation:weekly_green_metric -- --check
+
+  - label: "Check commit hash"
+    key: check-commit-hash
+    commands:
+      - bash .buildkite/release-automation/check-commit-hash.sh
+
+  - label: "Build update version binary"
+    key: build-update-version-zip
+    instance_type: default
+    commands:
+      - bazel build --build_python_zip --incompatible_use_python_toolchains=false --python_path=python //ci/ray_ci/automation:update_version
+      - cp bazel-bin/ci/ray_ci/automation/update_version /artifact-mount/
+
+  - label: "Trigger Postmerge test"
+    if: build.env("RAYCI_WEEKLY_RELEASE_NIGHTLY") != "1"
+    trigger: "postmerge"
+    key: trigger-postmerge
+    depends_on: check-commit-hash
+    build:
+      commit: "${BUILDKITE_COMMIT}"
+      branch: "${BUILDKITE_BRANCH}"
+      message: "Triggered by release-automation build #${BUILDKITE_BUILD_NUMBER}"
+      env:
+        RAYCI_RELEASE: 1
+        RAYCI_DISABLE_TEST_DB: "1"
+
+  - label: "Trigger Postmerge nightly build & test"
+    if: build.env("RAYCI_WEEKLY_RELEASE_NIGHTLY") == "1"
+    trigger: "postmerge"
+    key: trigger-postmerge-nightly
+    depends_on: check-commit-hash
+    build:
+      commit: "${BUILDKITE_COMMIT}"
+      branch: "${BUILDKITE_BRANCH}"
+      message: "Triggered by release-automation build #${BUILDKITE_BUILD_NUMBER}"
+      env:
+        RAYCI_RELEASE: "1"
+        RAYCI_SCHEDULE: "nightly"
+        RAYCI_DISABLE_TEST_DB: "1"
+
+  - label: "Check commit in nightly images"
+    key: check-ray-commit
+    if: build.branch !~ /^releases\// && build.env("RAYCI_WEEKLY_RELEASE_NIGHTLY") == "1"
+    depends_on: trigger-postmerge-nightly
+    allow_dependency_failure: true
+    commands:
+      - bazel run //ci/ray_ci/automation:check_nightly_ray_commit -- --ray_type=ray --expected_commit="${BUILDKITE_COMMIT}"
+
+  - label: "Trigger :kubernetes: Kuberay CI Tests"
+    if: build.env("RAYCI_WEEKLY_RELEASE_NIGHTLY") == "1"
+    trigger: "ray-ecosystem-ci-kuberay-ci"
+    key: trigger-kuberay
+    depends_on: check-ray-commit
+    build:
+      branch: "release-1.6"
+      message: "Triggered by release-automation build #${BUILDKITE_BUILD_NUMBER}"
+      env:
+        # KubeRay CI will pull an image based on this commit and the current date
+        RAY_NIGHTLY_COMMIT: "${BUILDKITE_COMMIT}"
+        IS_FROM_RAY_RELEASE_AUTOMATION: "1"
+
+  - label: "Trigger Postmerge MacOS test"
+    key: trigger-postmerge-macos
+    trigger: "postmerge-macos"
+    depends_on: check-commit-hash
+    build:
+      commit: "${BUILDKITE_COMMIT}"
+      branch: "${BUILDKITE_BRANCH}"
+      message: "Triggered by release-automation build #${BUILDKITE_BUILD_NUMBER}"
+      env:
+        RAYCI_RELEASE: "1"
+        RAYCI_DISABLE_TEST_DB: "1"
+
+  - block: "Trigger Release nightly test"
+    if: build.env("RAYCI_WEEKLY_RELEASE_NIGHTLY") != "1"
+    key: block-release-nightly-test
+    depends_on: check-commit-hash
+
+  - label: "Trigger Release nightly test"
+    key: trigger-release-nightly
+    trigger: "release"
+    depends_on: block-release-nightly-test
+    build:
+      commit: "${BUILDKITE_COMMIT}"
+      branch: "${BUILDKITE_BRANCH}"
+      message: "Nightly test - triggered by release-automation build #${BUILDKITE_BUILD_NUMBER}"
+      env:
+        AUTOMATIC: 1
+        RELEASE_FREQUENCY: "nightly"
+
+  - block: "Trigger Release nightly-3x test"
+    if: build.env("RAYCI_WEEKLY_RELEASE_NIGHLTY_3X") != "1"
+    key: block-release-nightly-3x-test
+    depends_on: check-commit-hash
+
+  - label: "Trigger Release nightly-3x test"
+    key: trigger-release-nightly-3x
+    depends_on: block-release-nightly-3x-test
+    trigger: "release"
+    build:
+      commit: "${BUILDKITE_COMMIT}"
+      branch: "${BUILDKITE_BRANCH}"
+      message: "Nightly-3x test - triggered by release-automation build #${BUILDKITE_BUILD_NUMBER}"
+      env:
+        AUTOMATIC: 1
+        RELEASE_FREQUENCY: "nightly-3x"
+
+  - block: "Trigger Release weekly test"
+    if: build.env("RAYCI_WEEKLY_RELEASE_WEEKLY") != "1"
+    key: block-release-weekly-test
+    depends_on: check-commit-hash
+
+  - label: "Trigger Release weekly test"
+    key: trigger-release-weekly
+    trigger: "release"
+    depends_on: block-release-weekly-test
+    build:
+      commit: "${BUILDKITE_COMMIT}"
+      branch: "${BUILDKITE_BRANCH}"
+      message: "Weekly test - triggered by release-automation build #${BUILDKITE_BUILD_NUMBER}"
+      env:
+        AUTOMATIC: 1
+        RELEASE_FREQUENCY: "weekly"

.buildkite/release-automation/set-ray-version.sh

@@ -0,0 +1,26 @@
+#!/bin/bash
+
+set -euo pipefail
+
+if [[ -z "${RAY_VERSION:-}" ]]; then
+    RAY_VERSION="$(python3 python/ray/_version.py | cut -d' ' -f1)"
+    if [[ "${RAY_VERSION}" =~ dev0 ]]; then
+        echo "RAY_VERSION is not set, value is ${RAY_VERSION}" >/dev/stderr
+        exit 1
+    fi
+fi
+
+if [[ "${RAY_COMMIT:-}" == "" ]]; then
+    if [[ "${BUILDKITE_COMMIT:-}" == "" ]]; then
+        echo "neither BUILDKITE_COMMIT nor RAY_COMMIT is set" >/dev/stderr
+        exit 1
+    fi
+    RAY_COMMIT="${BUILDKITE_COMMIT:-}"
+fi
+
+export RAY_VERSION
+export RAY_COMMIT
+
+# Print it out for information.
+echo "RAY_VERSION=$RAY_VERSION"
+echo "RAY_COMMIT=$RAY_COMMIT"

.buildkite/release-automation/verify-linux-wheels.sh

@@ -0,0 +1,37 @@
+#!/bin/bash
+
+set -euo pipefail
+
+set -x
+
+# Sets RAY_COMMIT and RAY_VERSION
+source .buildkite/release-automation/set-ray-version.sh
+
+if [[ "${PYTHON_VERSION}" == "" ]]; then
+	echo "Python version not set" >/dev/stderr
+	exit 1
+fi
+
+export PYTHON_VERSION
+
+export PATH="/usr/local/bin/miniforge3/bin:${PATH}"
+source "/usr/local/bin/miniforge3/etc/profile.d/conda.sh"
+
+conda create -n rayio python="${PYTHON_VERSION}" -y
+
+conda activate rayio
+
+pip install \
+    --index-url https://test.pypi.org/simple/ \
+    --extra-index-url https://pypi.org/simple \
+    "ray[cpp]==${RAY_VERSION}"
+
+(
+    cd release/util
+    python sanity_check.py --ray_version="${RAY_VERSION}" --ray_commit="${RAY_COMMIT}"
+)
+
+(
+    cd release/util
+    bash sanity_check_cpp.sh
+)

.buildkite/release-automation/verify-macos-wheels.sh

@@ -0,0 +1,72 @@
+#!/bin/bash
+
+set -euo pipefail
+
+set -x
+
+# TODO(#54047): Python 3.13 is skipped due to the bug
+# we should re-enable it when the bug is fixed.
+
+PYTHON_VERSIONS=("3.10" "3.11" "3.12")
+BAZELISK_VERSION="v1.16.0"
+
+# Sets RAY_VERSION and RAY_COMMIT
+source .buildkite/release-automation/set-ray-version.sh
+
+install_bazel() {
+    URL="https://github.com/bazelbuild/bazelisk/releases/download/${BAZELISK_VERSION}/bazelisk-darwin-arm64"
+
+    TARGET="$TMP_DIR/bin/bazel"
+    curl -sfL -R -o "${TARGET}" "${URL}"
+    chmod +x "${TARGET}"
+}
+
+install_miniforge() {
+    # Install miniforge3 based on the architecture used
+    mkdir -p "$TMP_DIR/miniforge3"
+    curl -sfL https://github.com/conda-forge/miniforge/releases/download/25.3.0-1/Miniforge3-25.3.0-1-MacOSX-arm64.sh -o "$TMP_DIR/miniforge3/miniforge.sh"
+    bash "$TMP_DIR/miniforge3/miniforge.sh" -b -u -p "$TMP_DIR/miniforge3"
+    rm -rf "$TMP_DIR/miniforge3/miniforge.sh"
+
+    # Initialize conda. This replaces calling `conda init bash`.
+    # Conda init command requires a shell restart which should not be done on BK.
+    source "$TMP_DIR/miniforge3/etc/profile.d/conda.sh"
+}
+
+run_sanity_check() {
+    local PYTHON_VERSION="$1"
+
+    conda create -n "rayio_${PYTHON_VERSION}" python="${PYTHON_VERSION}" -y
+    conda activate "rayio_${PYTHON_VERSION}"
+
+    pip install \
+        --index-url https://test.pypi.org/simple/ \
+        --extra-index-url https://pypi.org/simple \
+        "ray[cpp]==${RAY_VERSION}"
+    (
+        cd release/util
+        python sanity_check.py --ray_version="${RAY_VERSION}" --ray_commit="${RAY_COMMIT}"
+        bash sanity_check_cpp.sh
+    )
+    conda deactivate
+}
+
+_clean_up() {
+    bazel clean || true
+    rm -rf "$TMP_DIR"
+}
+
+# Create tmp directory unique for the run
+TMP_DIR="$(mktemp -d "$HOME/tmp.XXXXXXXXXX")"
+mkdir -p "$TMP_DIR/bin"
+export PATH="$TMP_DIR/bin:$PATH"
+
+trap _clean_up EXIT
+
+install_miniforge
+install_bazel
+
+# Install Ray & run sanity checks for each python version
+for V in "${PYTHON_VERSIONS[@]}"; do
+    run_sanity_check "$V"
+done

.buildkite/release-automation/wheels.rayci.yml

@@ -0,0 +1,96 @@
+group: Upload & Validate wheels
+steps:
+  - block: "Upload wheels from S3 to TestPyPI"
+    key: block-upload-wheels-testpypi
+    depends_on:
+      - forge
+
+  - label: "Upload wheels from S3 to TestPyPI"
+    key: upload-wheels-testpypi
+    depends_on:
+      - block-upload-wheels-testpypi
+    job_env: forge
+    instance_type: small_branch
+    commands:
+      - export RAY_VERSION="$RAY_VERSION"
+      - export RAY_COMMIT="$RAY_COMMIT"
+      - source .buildkite/release-automation/set-ray-version.sh
+      - bazel run //ci/ray_ci/automation:upload_wheels_pypi --
+        --ray_version="$$RAY_VERSION" --commit_hash="$$RAY_COMMIT"
+        --pypi_env=test
+
+  - block: "Download & validate Ray wheels from TestPyPI Linux x86_64"
+    key: block-validate-linux-x86_64-wheels
+    depends_on:
+      - forge
+
+  - label: "Linux x86_64 Python {{matrix}}"
+    key: validate-linux-x86_64-wheels
+    job_env: forge
+    depends_on:
+      - block-validate-linux-x86_64-wheels
+    commands:
+      - export PYTHON_VERSION={{matrix}}
+      - export RAY_VERSION="$RAY_VERSION"
+      - export RAY_COMMIT="$RAY_COMMIT"
+      - bash -i .buildkite/release-automation/verify-linux-wheels.sh
+    matrix:
+      - "3.10"
+      - "3.11"
+      - "3.12"
+      - "3.13"
+      - "3.14"
+
+  - block: "Download & validate Ray wheels from TestPyPI Linux arm64"
+    key: block-validate-linux-arm64-wheels
+    depends_on:
+      - forge-arm64
+
+  - label: "Linux arm64 Python {{matrix}}"
+    key: validate-linux-arm64-wheels
+    instance_type: medium-arm64
+    job_env: forge-arm64
+    depends_on:
+      - block-validate-linux-arm64-wheels
+    commands:
+      - export PYTHON_VERSION={{matrix}}
+      - export RAY_VERSION="$RAY_VERSION"
+      - export RAY_COMMIT="$RAY_COMMIT"
+      - bash -i .buildkite/release-automation/verify-linux-wheels.sh
+    matrix:
+      - "3.10"
+      - "3.11"
+      - "3.12"
+      - "3.13"
+      - "3.14"
+
+  - block: "Download & validate Ray wheels from TestPyPI Mac"
+    key: block-validate-macos-wheels
+    depends_on: []
+
+  - label: "MacOS arm64"
+    key: validate-macos-arm64-wheels
+    depends_on:
+      - block-validate-macos-wheels
+    job_env: MACOS
+    instance_type: macos-arm64
+    commands:
+      - bash .buildkite/release-automation/verify-macos-wheels.sh
+
+  - block: "Upload wheels to PyPI"
+    key: block-upload-wheels-pypi
+    depends_on: []
+
+  - label: "Upload wheels to PyPI"
+    key: upload-wheels-pypi
+    depends_on:
+      - block-upload-wheels-pypi
+    job_env: forge
+    instance_type: small_branch
+    commands:
+      - export RAY_VERSION="$RAY_VERSION"
+      - export RAY_COMMIT="$RAY_COMMIT"
+      - source .buildkite/release-automation/set-ray-version.sh
+      - bazel run //ci/ray_ci/automation:upload_wheels_pypi --
+        --ray_version="$$RAY_VERSION" --commit_hash="$$RAY_COMMIT"
+        --pypi_env=prod

.buildkite/release/_forge.rayci.yml

@@ -0,0 +1 @@
+../_forge.rayci.yml

.buildkite/release/_images.rayci.yml

@@ -0,0 +1 @@
+../_images.rayci.yml

.buildkite/release/_wheel-build.rayci.yml

@@ -0,0 +1 @@
+../_wheel-build.rayci.yml

.buildkite/release/build.rayci.yml

@@ -0,0 +1,238 @@
+group: release build
+steps:
+  - name: raycpubaseextra-testdeps
+    label: "wanda: ray.py{{array.python}}.cpu.base-extra-testdeps"
+    wanda: docker/base-extra-testdeps/cpu.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      IMAGE_TYPE: "ray"
+    depends_on:
+      - raycpubaseextra($)
+
+  - name: raycudabaseextra-testdeps
+    label: "wanda: ray.py{{array.python}}.cu{{array.cuda}}.base-extra-testdeps"
+    wanda: docker/base-extra-testdeps/cuda.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+      cuda:
+        - "12.3.2-cudnn9"
+        - "13.0.0-cudnn"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      CUDA_VERSION: "{{array.cuda}}"
+      IMAGE_TYPE: "ray"
+    depends_on:
+      - raycudabaseextra($)
+
+  - name: ray-llmbaseextra-testdeps
+    label: "wanda: ray.py{{array.python}}.llm.base-extra-testdeps (cuda {{array.cuda}})"
+    wanda: docker/base-extra-testdeps/cuda.wanda.yaml
+    array:
+      python:
+        - "3.12"
+      cuda:
+        - "13.0.0-cudnn"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      CUDA_VERSION: "{{array.cuda}}"
+      IMAGE_TYPE: "ray-llm"
+    depends_on:
+      - ray-llmbaseextra($)
+
+  - name: ray-mlcudabaseextra-testdeps
+    label: "wanda: ray.py{{array.python}}.cu{{array.cuda}}.ml.base-extra-testdeps"
+    wanda: docker/base-extra-testdeps/cuda.wanda.yaml
+    array:
+      python:
+        - "3.10"
+      cuda:
+        - "12.1.1-cudnn8"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      CUDA_VERSION: "{{array.cuda}}"
+      IMAGE_TYPE: "ray-ml"
+    depends_on:
+      - ray-mlcudabaseextra($)
+
+  - name: ray-anyscale-cpu-build
+    label: "wanda: ray-anyscale py{{array.python}} cpu"
+    wanda: ci/docker/ray-anyscale-cpu.wanda.yaml
+    env_file: rayci.env
+    array:
+      python:
+        # This list should be kept in sync with the list of supported Python in
+        # release test suite
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      ARCH_SUFFIX: ""
+    tags:
+      - oss
+    depends_on:
+      - ray-wheel-build($)
+      - raycpubaseextra-testdeps($)
+
+  - name: ray-anyscale-cuda-build
+    label: "wanda: ray-anyscale py{{array.python}} {{array.gpu}}"
+    wanda: ci/docker/ray-anyscale-cuda.wanda.yaml
+    env_file: rayci.env
+    array:
+      gpu:
+        - "cu12.3.2-cudnn9"
+        - "cu13.0.0-cudnn"
+      python:
+        # This list should be kept in sync with the list of supported Python in
+        # release test suite
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      GPU: "{{array.gpu}}"
+      ARCH_SUFFIX: ""
+    tags:
+      - oss
+    depends_on:
+      - ray-wheel-build($)
+      - raycudabaseextra-testdeps($)
+
+  - label: ":crane: publish: ray-anyscale py{{array.python}} cpu"
+    key: anyscalecpubuild
+    instance_type: release-medium
+    mount_buildkite_agent: true
+    tags:
+      - oss
+    commands:
+      - bazel run //ci/ray_ci/automation:push_release_test_image --
+        --python-version {{array.python}}
+        --platform cpu
+        --image-type ray
+        --upload
+    depends_on:
+      - forge
+      - ray-anyscale-cpu-build($)
+    array:
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+
+  - label: ":crane: publish: ray-anyscale py{{array.python}} {{array.gpu}}"
+    key: anyscalecudabuild
+    instance_type: release-medium
+    mount_buildkite_agent: true
+    tags:
+      - oss
+    commands:
+      - bazel run //ci/ray_ci/automation:push_release_test_image --
+        --python-version {{array.python}}
+        --platform {{array.gpu}}
+        --image-type ray
+        --upload
+    depends_on:
+      - forge
+      - ray-anyscale-cuda-build($)
+    array:
+      gpu:
+        - cu12.3.2-cudnn9
+        - cu13.0.0-cudnn
+      python:
+        - "3.10"
+        - "3.11"
+        - "3.12"
+        - "3.13"
+
+  - name: ray-llm-anyscale-cuda-build
+    label: "wanda: ray-llm-anyscale py{{array.python}} {{array.gpu}}"
+    wanda: ci/docker/ray-llm-anyscale-cuda.wanda.yaml
+    env_file: rayci.env
+    array:
+      gpu:
+        - "cu13.0.0-cudnn"
+      python:
+        - "3.12"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      GPU: "{{array.gpu}}"
+      ARCH_SUFFIX: ""
+    tags:
+      - oss
+    depends_on:
+      - ray-wheel-build($)
+      - ray-llmbaseextra-testdeps($)
+
+  - label: ":crane: publish: ray-llm-anyscale py{{array.python}} {{array.gpu}}"
+    key: anyscalellmbuild
+    instance_type: release-medium
+    mount_buildkite_agent: true
+    tags:
+      - oss
+    commands:
+      - bazel run //ci/ray_ci/automation:push_release_test_image --
+        --python-version {{array.python}}
+        --platform {{array.gpu}}
+        --image-type ray-llm
+        --upload
+    depends_on:
+      - forge
+      - ray-llm-anyscale-cuda-build($)
+    array:
+      gpu:
+        - cu13.0.0-cudnn
+      python:
+        - "3.12"
+
+  - name: ray-ml-anyscale-cuda-build
+    label: "wanda: ray-ml-anyscale py{{array.python}} {{array.gpu}}"
+    wanda: ci/docker/ray-ml-anyscale-cuda.wanda.yaml
+    env_file: rayci.env
+    array:
+      gpu:
+        - "cu12.1.1-cudnn8"
+      python:
+        # This list should be kept in sync with the list of supported Python in
+        # release test suite
+        - "3.10"
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      GPU: "{{array.gpu}}"
+      ARCH_SUFFIX: ""
+    tags:
+      - oss
+    depends_on:
+      - ray-wheel-build($)
+      - ray-mlcudabaseextra-testdeps($)
+
+  - label: ":crane: publish: ray-ml-anyscale py{{array.python}} cu12.1.1-cudnn8"
+    key: anyscalemlbuild
+    instance_type: release-medium
+    mount_buildkite_agent: true
+    tags:
+      - oss
+    commands:
+      - bazel run //ci/ray_ci/automation:push_release_test_image --
+        --python-version {{array.python}}
+        --platform cu12.1.1-cudnn8
+        --image-type ray-ml
+        --upload
+    depends_on:
+      - forge
+      - ray-ml-anyscale-cuda-build($)
+    array:
+      python:
+        - "3.10"

.buildkite/release/config.yml

@@ -0,0 +1,25 @@
+name: ray-release
+artifacts_bucket: ray-ci-artifact-branch-public
+ci_temp: s3://ray-ci-artifact-branch-public/ci-temp/
+ci_work_repo: 029272617770.dkr.ecr.us-west-2.amazonaws.com/rayproject/citemp
+forge_prefix: cr.ray.io/rayproject/
+builder_queues:
+  builder: builder_queue_branch
+runner_queues:
+  release: release_queue_small
+  release-medium: release_queue_medium
+buildkite_dirs:
+  - .buildkite/release
+env:
+  BUILDKITE_BAZEL_CACHE_URL: https://bazel-cache-dev.s3.us-west-2.amazonaws.com
+  RAYCI_SKIP_UPLOAD: "true"
+hook_env_keys:
+  - RAYCI_CHECKOUT_DIR
+skip_tags:
+  - disabled
+  - skip-on-release-tests
+build_env_keys:
+  - AUTOMATIC
+  - RELEASE_FREQUENCY
+docker_plugin:
+  allow_mount_buildkite_agent: true

.buildkite/release/custom-image-build-and-test-init.sh

@@ -0,0 +1,73 @@
+#!/bin/bash
+
+set -euo pipefail
+
+if [[ ${BUILDKITE_COMMIT} == "HEAD" ]]; then
+  BUILDKITE_COMMIT="$(git rev-parse HEAD)"
+  export BUILDKITE_COMMIT
+fi
+
+# Get build ID from environment variables
+BUILD_ID="${RAYCI_BUILD_ID:-}"
+
+if [[ -z "${BUILD_ID}" ]]; then
+    if [[ -n "${BUILDKITE_BUILD_ID:-}" ]]; then
+        # Generate SHA256 hash of BUILDKITE_BUILD_ID and take first 8 chars
+        BUILD_ID=$(echo -n "${BUILDKITE_BUILD_ID}" | sha256sum | cut -c1-8)
+    fi
+fi
+
+export RAYCI_BUILD_ID="${BUILD_ID}"
+echo "RAYCI_BUILD_ID: ${RAYCI_BUILD_ID}"
+
+if [[ "${AUTOMATIC:-0}" == "1" && -n "${RAYCI_SELECT:-}" ]]; then
+  echo "Skipping custom image build and test init because RAYCI_SELECT is set"
+  echo "RAYCI_SELECT: ${RAYCI_SELECT}"
+  exit 0
+fi
+
+aws ecr get-login-password --region us-west-2 | \
+    docker login --username AWS --password-stdin 029272617770.dkr.ecr.us-west-2.amazonaws.com
+
+bash release/gcloud_docker_login.sh release/aws2gce_iam.json
+export PATH="${PWD}/google-cloud-sdk/bin:$PATH"
+
+
+echo "--- Install Bazel"
+curl -sSfLo /tmp/bazel https://github.com/bazelbuild/bazelisk/releases/download/v1.19.0/bazelisk-linux-amd64
+chmod +x /tmp/bazel
+
+
+echo "--- Install uv"
+
+UV_PYTHON_VERSION=3.10
+curl -LsSf https://astral.sh/uv/install.sh | sh
+UV_BIN="${HOME}/.local/bin/uv"
+"${UV_BIN}" python install "${UV_PYTHON_VERSION}"
+UV_PYTHON_BIN="$("${UV_BIN}" python find --no-project "${UV_PYTHON_VERSION}")"
+
+echo "--- Generate custom build steps"
+
+if [[ "${AUTOMATIC:-0}" == "1" && "${BUILDKITE_BRANCH}" == "master" ]]; then
+  export REPORT_TO_RAY_TEST_DB=1
+fi
+
+RUN_FLAGS=()
+if [[ "${AUTOMATIC:-0}" == "0" || "${BUILDKITE_BRANCH}" == "releases/"* ]]; then
+  RUN_FLAGS+=(--run-jailed-tests)
+fi
+if [[ "${BUILDKITE_BRANCH}" != "releases/"* ]]; then
+  RUN_FLAGS+=(--run-unstable-tests)
+fi
+
+/tmp/bazel build --python_path="${UV_PYTHON_BIN}" \
+  --build_python_zip --enable_runfiles \
+  --incompatible_use_python_toolchains=false \
+  //release:custom_image_build_and_test_init
+
+BUILD_WORKSPACE_DIRECTORY="${PWD}" bazel-bin/release/custom_image_build_and_test_init \
+  "${RUN_FLAGS[@]}" \
+  --custom-build-jobs-output-file .buildkite/release/custom_build_jobs.rayci.yaml \
+  --test-jobs-output-file .buildkite/release/release_tests.json \
+  --rayci-select-output-file /tmp/rayci_select.txt \
+  --upload-to-buildkite

.buildkite/rllib.rayci.yml

@@ -0,0 +1,273 @@
+group: rllib tests
+depends_on:
+  - forge
+  - ray-core-build(*)
+  - ray-dashboard-build
+steps:
+  # builds
+  - name: rllibbuild-multipy
+    label: "wanda: rllibbuild-py{{array.python}}"
+    wanda: ci/docker/rllib.build.wanda.yaml
+    tags: cibase
+    array:
+      python:
+        - "3.10"
+        - "3.12"
+    env:
+      PYTHON: "{{array.python}}"
+      BASE_TYPE: "ml"
+      BUILD_VARIANT: "build"
+      RAYCI_IS_GPU_BUILD: "false"
+    depends_on: oss-ci-base_ml-multipy($)
+
+  - name: rllibgpubuild
+    wanda: ci/docker/rllib.build.wanda.yaml
+    depends_on: oss-ci-base_gpu-multipy(python=3.12)
+    env:
+      PYTHON: "3.12"
+      BASE_TYPE: "gpu"
+      BUILD_VARIANT: "gpubuild"
+      RAYCI_IS_GPU_BUILD: "true"
+    tags: cibase
+
+  # tests
+  - label: ":brain: rllib: component testing"
+    tags: rllib_directly
+    parallelism: 4
+    instance_type: large
+    commands:
+      # All tests to with tags for components without gpu or multi_gpu tags
+      - bazel run //ci/ray_ci:test_in_docker -- //rllib/... rllib
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 3
+        --only-tags env,evaluation,models,offline,policy,utils,algorithms,callbacks,core
+        --except-tags gpu,multi_gpu,manual
+        --test-env RAY_USE_MULTIPROCESSING_CPU_COUNT=1
+        --build-name rllibbuild-py3.12
+        --python-version 3.12
+    depends_on: rllibbuild-multipy(python=3.12)
+
+  - label: ":brain: rllib: examples"
+    tags: rllib
+    parallelism: 6
+    instance_type: large
+    commands:
+      # Tests all examples without gpu, multi_gpu or examples_use_all_cores tag
+      - bazel run //ci/ray_ci:test_in_docker -- //rllib/... rllib
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 2
+        --only-tags examples
+        --except-tags gpu,multi_gpu,manual,examples_use_all_core
+        --test-env RAY_USE_MULTIPROCESSING_CPU_COUNT=1
+        --build-name rllibbuild-py3.12
+        --python-version 3.12
+      # Tests all examples without gpu or multi_gpu
+      - bazel run //ci/ray_ci:test_in_docker -- //rllib/... rllib
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}"
+        --only-tags examples_use_all_core
+        --except-tags gpu,multi_gpu,manual
+        --test-env RAY_USE_MULTIPROCESSING_CPU_COUNT=1
+        --build-name rllibbuild-py3.12
+        --python-version 3.12
+        --skip-ray-installation # reuse the same docker image as the previous run
+    depends_on: rllibbuild-multipy(python=3.12)
+
+  - label: ":brain: rllib: learning tests"
+    tags: rllib
+    parallelism: 5
+    instance_type: large
+    commands:
+      # learning tests without a gpu
+      - bazel run //ci/ray_ci:test_in_docker -- //rllib/... rllib
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 3
+        --only-tags learning_tests
+        --except-tags gpu,multi_gpu,learning_tests_use_all_core,manual
+        --test-arg --framework=torch
+        --build-name rllibbuild-py3.12
+        --python-version 3.12
+      # learning tests without a gpu but use all cores
+      - bazel run //ci/ray_ci:test_in_docker -- //rllib/... rllib
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}"
+        --only-tags learning_tests_use_all_core
+        --except-tags gpu,multi_gpu,manual
+        --test-arg --framework=torch
+        --build-name rllibbuild-py3.12
+        --python-version 3.12
+        --skip-ray-installation # reuse the same docker image as the previous run
+    depends_on: rllibbuild-multipy(python=3.12)
+
+  - label: ":brain: rllib: gpu tests"
+    tags:
+      - rllib_gpu
+      - gpu
+      - skip-on-microcheck
+    parallelism: 5
+    instance_type: gpu
+    commands:
+      # All gpu tagged tests
+      - bazel run //ci/ray_ci:test_in_docker -- //rllib/... rllib
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}"
+        --only-tags gpu
+        --except-tags multi_gpu,manual
+        --test-env=RAY_USE_MULTIPROCESSING_CPU_COUNT=1
+        --test-env=RLLIB_NUM_GPUS=1
+        --build-name rllibgpubuild-py3.12
+        --python-version 3.12
+    depends_on: rllibgpubuild
+
+  - label: ":brain: rllib: multi-gpu tests"
+    tags:
+      - rllib_gpu
+      - gpu
+      - skip-on-microcheck
+    parallelism: 5
+    instance_type: gpu-large
+    commands:
+      # All multi-gpu tagged tests (including all learning, examples and component testings)
+      - bazel run //ci/ray_ci:test_in_docker -- //rllib/... rllib
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}"
+        --parallelism-per-worker 2
+        --gpus 4
+        --only-tags multi_gpu
+        --except-tags manual
+        --build-name rllibgpubuild-py3.12
+        --python-version 3.12
+    depends_on: rllibgpubuild
+
+  - label: ":brain: rllib: doc tests"
+    if: '!(build.pull_request.labels includes "docs-go")'
+    tags:
+      - rllib_directly
+      - doc
+      - skip-on-microcheck
+    instance_type: medium
+    commands:
+      # doc tests
+      - bazel run //ci/ray_ci:test_in_docker -- python/ray/... //doc/... rllib
+        --only-tags doctest
+        --except-tags gpu,manual
+        --parallelism-per-worker 2
+        --build-name rllibbuild-py3.12
+        --python-version 3.12
+      # doc examples
+      - bazel run //ci/ray_ci:test_in_docker -- //doc/... rllib
+        --except-tags gpu,post_wheel_build,timeseries_libs,doctest
+        --parallelism-per-worker 2
+        --build-name rllibbuild-py3.12
+        --python-version 3.12
+        --skip-ray-installation # reuse the same docker image as the previous run
+      # documentation test
+      - bazel run //ci/ray_ci:test_in_docker -- //rllib/... rllib
+        --only-tags documentation
+        --parallelism-per-worker 2
+        --build-name rllibbuild-py3.12
+        --python-version 3.12
+        --skip-ray-installation # reuse the same docker image as the previous run
+    depends_on: rllibbuild-multipy(python=3.12)
+
+  - label: ":brain: rllib: python 3.10 component testing ({{matrix.worker_id}})"
+    if: build.pull_request.labels includes "continuous-build" || pipeline.id == "0189e759-8c96-4302-b6b5-b4274406bf89" || pipeline.id == "018f4f1e-1b73-4906-9802-92422e3badaa"
+    tags: rllib_directly
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //rllib/... rllib
+        --workers 4 --worker-id {{matrix.worker_id}} --parallelism-per-worker 3
+        --only-tags env,evaluation,models,offline,policy,utils,algorithms,callbacks,core
+        --except-tags gpu,multi_gpu,manual
+        --test-env RAY_USE_MULTIPROCESSING_CPU_COUNT=1
+        --build-name rllibbuild-py3.10
+        --python-version 3.10
+    depends_on: rllibbuild-multipy(python=3.10)
+    matrix:
+      setup:
+        worker_id: ["0", "1", "2", "3"]
+
+  - label: ":brain: rllib: flaky component & examples tests"
+    key: rllib_flaky_tests_02
+    tags:
+      - rllib
+      - rllib_flaky
+      - skip-on-premerge
+    instance_type: large
+    commands:
+      # flaky components
+      - bazel run //ci/ray_ci:test_in_docker -- //rllib/... rllib  --run-flaky-tests --parallelism-per-worker 3
+        --only-tags env,evaluation,models,offline,policy,utils,algorithms,callbacks,core
+        --except-tags learning_tests,examples,documentation,gpu,multi_gpu,manual
+        --test-env RAY_USE_MULTIPROCESSING_CPU_COUNT=1
+        --build-name rllibbuild-py3.12
+        --python-version 3.12
+
+      # flaky examples
+      - bazel run //ci/ray_ci:test_in_docker -- //rllib/... rllib  --run-flaky-tests --parallelism-per-worker 3
+        --only-tags examples
+        --except-tags multi_gpu,gpu,manual,examples_use_all_core
+        --test-env RAY_USE_MULTIPROCESSING_CPU_COUNT=1
+        --build-name rllibbuild-py3.12
+        --python-version 3.12
+        --skip-ray-installation # reuse the same docker image as the previous run
+
+      # flaky examples use all core
+      - bazel run //ci/ray_ci:test_in_docker -- //rllib/... rllib  --run-flaky-tests --parallelism-per-worker 3
+        --only-tags examples_use_all_core
+        --except-tags gpu,multi_gpu,manual
+        --test-env RAY_USE_MULTIPROCESSING_CPU_COUNT=1
+        --build-name rllibbuild-py3.12
+        --python-version 3.12
+        --skip-ray-installation # reuse the same docker image as the previous run
+    depends_on: rllibbuild-multipy(python=3.12)
+    soft_fail: true
+
+  - label: ":brain: rllib: flaky learning tests"
+    key: rllib_flaky_tests_01
+    tags:
+      - rllib
+      - rllib_flaky
+      - skip-on-premerge
+    instance_type: large
+    commands:
+      # torch
+      - bazel run //ci/ray_ci:test_in_docker -- //rllib/... rllib --run-flaky-tests
+        --only-tags learning_tests
+        --except-tags gpu,multi_gpu,manual
+        --test-arg --framework=torch
+        --build-name rllibbuild-py3.12
+        --python-version 3.12
+    depends_on: rllibbuild-multipy(python=3.12)
+    soft_fail: true
+
+  - label: ":brain: rllib: flaky gpu tests"
+    key: rllib_flaky_gpu_tests
+    tags:
+      - rllib_gpu
+      - gpu
+      - rllib_flaky
+      - skip-on-premerge
+    instance_type: gpu
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //rllib/... rllib --run-flaky-tests
+        --only-tags gpu
+        --except-tags multi_gpu,manual
+        --test-env=RAY_USE_MULTIPROCESSING_CPU_COUNT=1
+        --test-env=RLLIB_NUM_GPUS=1
+        --build-name rllibgpubuild-py3.12
+        --python-version 3.12
+    depends_on: rllibgpubuild
+    soft_fail: true
+
+  - label: ":brain: rllib: flaky multi-gpu tests"
+    key: rllib_flaky_multi_gpu_tests
+    tags:
+      - rllib_gpu
+      - gpu
+      - rllib_flaky
+      - skip-on-premerge
+    instance_type: gpu-large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //rllib/... rllib --run-flaky-tests
+        --parallelism-per-worker 2
+        --gpus 4
+        --only-tags multi_gpu
+        --except-tags manual
+        --build-name rllibgpubuild-py3.12
+        --python-version 3.12
+    depends_on: rllibgpubuild
+    soft_fail: true

.buildkite/serve.rayci.yml

@@ -0,0 +1,293 @@
+group: serve tests
+depends_on:
+  - forge
+  - oss-ci-base_build-multipy(*)
+  - ray-core-build(*)
+  - ray-dashboard-build
+steps:
+  # builds
+  - name: servebuild-multipy
+    label: "wanda: servebuild-py{{array.python}}"
+    wanda: ci/docker/serve.build.wanda.yaml
+    array:
+      python:
+        - "3.10"
+        - "3.12"
+    env:
+      PYTHON: "{{array.python}}"
+    tags: cibase
+
+
+  - name: servetracingbuild
+    wanda: ci/docker/servetracing.build.wanda.yaml
+
+  - name: minbuild-serve
+    label: "wanda: minbuild-{{array.extra}}-py{{array.python}}"
+    wanda: ci/docker/min.build.wanda.yaml
+    depends_on: oss-ci-base_test-multipy(python=3.10)
+    array:
+      python: ["3.10"]
+      extra: ["serve", "default"]
+    env:
+      PYTHON_VERSION: "{{array.python}}"
+      EXTRA_DEPENDENCY: "{{array.extra}}"
+    tags: cibase
+
+  # tests
+  - label: ":ray-serve: serve: tests"
+    parallelism: 2
+    tags:
+      - serve
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/serve/... //python/ray/tests/...  serve
+        --except-tags post_wheel_build,gpu,ha_integration,serve_tracing,direct_ingress,haproxy
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 3
+        --build-name servebuild-py3.10 --test-env=EXPECTED_PYTHON_VERSION=3.10 --python-version 3.10
+    depends_on: servebuild-multipy(python=3.10)
+
+  - label: ":ray-serve: serve: gRPC tests"
+    parallelism: 2
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/serve/... //python/ray/tests/...  serve
+        --except-tags post_wheel_build,gpu,ha_integration,haproxy
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 3
+        --build-name servebuild-py3.10 --python-version 3.10
+        --test-env=RAY_SERVE_USE_GRPC_BY_DEFAULT=1
+        --test-env=RAY_SERVE_REPLICA_GRPC_MAX_MESSAGE_LENGTH=10500000
+    depends_on: servebuild-multipy(python=3.10)
+    tags:
+      - serve
+
+  - label: ":ray-serve: serve: same event loop tests"
+    parallelism: 2
+    tags:
+      - serve
+      - skip-on-premerge
+    instance_type: large
+    soft_fail: true
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/serve/... //python/ray/tests/...  serve
+        --except-tags post_wheel_build,gpu,ha_integration,serve_tracing,direct_ingress,haproxy
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 3
+        --build-name servebuild-py3.10 --test-env=EXPECTED_PYTHON_VERSION=3.10 --test-env=RAY_SERVE_RUN_USER_CODE_IN_SEPARATE_THREAD=0
+        --python-version 3.10
+    depends_on: servebuild-multipy(python=3.10)
+
+  - label: ":ray-serve: serve: python {{array.python}} tests ({{array.worker_id}})"
+    key: serve_python_tests
+    if: build.pull_request.labels includes "continuous-build" || pipeline.id == "0189e759-8c96-4302-b6b5-b4274406bf89" || pipeline.id == "018f4f1e-1b73-4906-9802-92422e3badaa"
+    tags:
+      - serve
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/serve/... //python/ray/tests/...  serve
+        --except-tags post_wheel_build,gpu,ha_integration,serve_tracing,direct_ingress,haproxy
+        --workers 2 --worker-id {{array.worker_id}} --parallelism-per-worker 3
+        --python-version {{array.python}}
+        --test-env=EXPECTED_PYTHON_VERSION={{array.python}}
+    depends_on: servebuild-multipy($)
+    array:
+      python: ["3.12"]
+      worker_id: ["0", "1"]
+
+  - label: ":ray-serve: serve: release tests"
+    tags:
+      - serve
+      - release_tests
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //release/... serve --parallelism-per-worker 3
+        --build-name servebuild-py3.10
+        --python-version 3.10
+    depends_on: servebuild-multipy(python=3.10)
+
+  - label: ":ray-serve: serve: wheel tests"
+    tags:
+      - serve
+      - linux_wheels
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/serve/... //doc/... serve
+        --build-type wheel
+        --parallelism-per-worker 3
+        --only-tags post_wheel_build
+        --test-env=RAY_CI_POST_WHEEL_TESTS=True
+        --build-name servebuild-py3.10
+        --python-version 3.10
+    depends_on:
+      - manylinux-x86_64
+      - servebuild-multipy(python=3.10)
+      - forge
+      - ray-wheel-build(python=3.10)
+
+  - label: ":ray-serve: serve: doc tests"
+    if: '!(build.pull_request.labels includes "docs-go")'
+    tags:
+      - serve
+      - doc
+    instance_type: large
+    commands:
+      # doc tests
+      - bazel run //ci/ray_ci:test_in_docker -- python/ray/... //doc/... serve
+        --only-tags doctest
+        --parallelism-per-worker 3
+        --build-name servebuild-py3.10
+        --python-version 3.10
+      # doc examples
+      - bazel run //ci/ray_ci:test_in_docker -- //doc/... serve
+        --except-tags gpu,post_wheel_build,timeseries_libs,doctest
+        --parallelism-per-worker 3
+        --skip-ray-installation
+        --build-name servebuild-py3.10
+        --python-version 3.10
+    depends_on: servebuild-multipy(python=3.10)
+
+  - label: ":ray-serve: serve: default minimal"
+    tags:
+      - serve
+      - min_build
+    instance_type: small
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/dashboard/... serve
+        --parallelism-per-worker 2
+        --build-name minbuild-default-py3.10
+        --python-version 3.10
+        --test-env=RAY_DEFAULT=1
+        --only-tags minimal
+    depends_on: minbuild-serve(python=3.10, extra=default)
+
+  - label: ":ray-serve: serve: serve minimal"
+    tags:
+      - serve
+      - min_build
+    instance_type: small
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/serve/tests/... serve
+        --parallelism-per-worker 2
+        --build-name minbuild-serve-py3.10
+        --python-version 3.10
+        --test-env=EXPECTED_PYTHON_VERSION=3.10
+        --test-env=RAY_DEFAULT=1
+        --only-tags minimal
+    depends_on: minbuild-serve(python=3.10, extra=serve)
+
+  - label: ":ray-serve: serve: dashboard tests"
+    tags:
+      - serve
+      - dashboard
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- python/ray/dashboard/... serve
+        --parallelism-per-worker 3
+        --build-name servebuild-py3.10
+        --python-version 3.10
+    depends_on: servebuild-multipy(python=3.10)
+
+  - label: ":ray-serve: serve: HA integration tests"
+    tags:
+      - serve
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:build_in_docker -- docker --platform cpu --canonical-tag ha_integration --python-version 3.10
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/serve/tests/... serve
+        --only-tags ha_integration --python-version 3.10 --build-name servebuild-py3.10
+    depends_on:
+      - manylinux-x86_64
+      - forge
+      - raycpubase(python=3.10)
+      - servebuild-multipy(python=3.10)
+
+  - label: ":ray-serve: serve: tracing tests"
+    tags:
+      - serve
+    instance_type: medium
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/serve/... //python/ray/tests/...  serve
+        --only-tags serve_tracing --build-name servetracingbuild
+        --python-version 3.10
+    depends_on: servetracingbuild
+
+  - label: ":ray-serve: serve: HAProxy tests"
+    parallelism: 3
+    tags:
+      - serve
+    instance_type: large
+    commands:
+      # Exit 42 skips whole-step retry (per @kouroshHakha); per-test retry is enough.
+      - bazel run //ci/ray_ci:test_in_docker -- $(cat ci/ray_ci/serve_hap_test_names.txt) serve
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}"
+        --build-name servebuild-py3.10 --python-version 3.10
+        --test-env=RAY_SERVE_ENABLE_HA_PROXY=1
+        --test-env=RAY_SERVE_ENABLE_DIRECT_INGRESS=0
+        --test-env=RAY_SERVE_DIRECT_INGRESS_MIN_DRAINING_PERIOD_S=0.01
+        --test-env=SERVE_SOCKET_REUSE_PORT_ENABLED=1 || exit 42
+    depends_on: servebuild-multipy(python=3.10)
+
+  - label: ":ray-serve: serve: direct ingress tests"
+    tags:
+      - serve
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- $(cat ci/ray_ci/serve_di_test_names.txt) serve
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 3
+        --build-name servebuild-py3.10 --python-version 3.10
+        --test-env=RAY_SERVE_ENABLE_DIRECT_INGRESS=1
+        --test-env=RAY_SERVE_DIRECT_INGRESS_MIN_DRAINING_PERIOD_S=0.01
+    depends_on: servebuild-multipy(python=3.10)
+
+  - label: ":ray-serve: serve: direct ingress tests (same loop)"
+    tags:
+      - serve
+    instance_type: large
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- $(cat ci/ray_ci/serve_di_test_names.txt) serve
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 3
+        --build-name servebuild-py3.10 --python-version 3.10
+        --test-env=RAY_SERVE_ENABLE_DIRECT_INGRESS=1
+        --test-env=RAY_SERVE_DIRECT_INGRESS_MIN_DRAINING_PERIOD_S=0.01
+        --test-env=RAY_SERVE_RUN_USER_CODE_IN_SEPARATE_THREAD=0
+    depends_on: servebuild-multipy(python=3.10)
+
+  - label: ":ray-serve: serve: doc gpu tests"
+    if: '!(build.pull_request.labels includes "docs-go")'
+    tags:
+      - serve
+      - doc
+      - gpu
+    instance_type: gpu
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //doc/... serve
+        --build-name docgpubuild-py3.10
+        --only-tags gpu --python-version 3.10
+    depends_on: docgpubuild
+
+  - label: ":ray-serve: serve: flaky tests"
+    key: serve_flaky_tests
+    tags:
+      - serve
+      - flaky
+      - skip-on-premerge
+    instance_type: large
+    soft_fail: true
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //... serve --run-flaky-tests --parallelism-per-worker 3
+        --python-version 3.10 --build-name servebuild-py3.10
+        --except-tags gpu
+    depends_on: servebuild-multipy(python=3.10)
+
+  - label: ":ray-serve: serve: flaky gpu tests"
+    key: serve_flaky_gpu_tests
+    tags:
+      - serve
+      - gpu
+      - flaky
+      - skip-on-premerge
+    instance_type: gpu
+    soft_fail: true
+    commands:
+      - bazel run //ci/ray_ci:test_in_docker -- //... serve --run-flaky-tests
+        --python-version 3.10 --build-name docgpubuild-py3.10
+        --only-tags gpu
+    depends_on: docgpubuild

.buildkite/test.rules.test.txt

@@ -0,0 +1,115 @@
+# Test cases for Ray CI test rules
+# Based on ci/pipeline/test_conditional_testing.py _TESTS_YAML
+#
+# Format: file: tag1 tag2 tag3
+
+# === CI/Pipeline ===
+
+ci/pipeline/test_conditional_testing.py: tools
+
+# === Ray Libraries ===
+
+python/ray/data/__init__.py: data
+python/ray/air/__init__.py: ml train train_gpu tune data linux_wheels
+python/ray/llm/llm.py: llm
+python/ray/workflow/workflow.py: workflow
+python/ray/tune/tune.py: ml train tune linux_wheels
+python/ray/train/train.py: ml train train_gpu linux_wheels
+python/ray/serve/serve.py: serve linux_wheels java
+python/ray/dashboard/dashboard.py: dashboard linux_wheels core_python
+
+# === Ray Utilities ===
+
+python/ray/util/dask/dask.py: core_python dask
+python/ray/dag/dag.py: core_python cgraphs_direct_transport
+python/ray/experimental/rdt/rdt_manager.py: core_python cgraphs_direct_transport
+
+# === RLlib ===
+
+rllib/rllib.py: rllib rllib_gpu rllib_directly
+
+# === Python Core ===
+
+python/core.py: ml tune train data serve llm core_python dashboard linux_wheels macos_wheels java
+python/setup.py: ml tune train serve workflow data core_python dashboard linux_wheels macos_wheels java python_dependencies min_build
+python/requirements/test-requirements.txt: ml tune train serve workflow data core_python dashboard linux_wheels macos_wheels java python_dependencies min_build
+python/requirements_compiled.txt: ml tune train serve workflow data core_python dashboard linux_wheels macos_wheels java python_dependencies min_build
+python/requirements_compiled_py3.13.txt: ml tune train serve workflow data core_python dashboard linux_wheels macos_wheels java python_dependencies min_build
+python/_raylet.pyx: ml tune train data serve llm core_python dashboard linux_wheels macos_wheels java
+
+# === Raydepsets lock files and configs ===
+# macos_depset lock is consumed by the mac smoke test (macos_wheels) AND
+# also needs to run the raydepsets --check verification (python_dependencies).
+python/deplocks/ci/macos_depset_py3.10.lock: macos_wheels python_dependencies
+# Other deplock updates should NOT trigger the mac smoke test (no macos_wheels).
+python/deplocks/base_deps/ray_base_deps_py3.10.lock: ml tune train serve workflow data core_python dashboard linux_wheels java python_dependencies min_build
+python/deplocks/ci/data-base-ci_depset_py3.10.lock: ml tune train serve workflow data core_python dashboard linux_wheels java python_dependencies min_build
+# LLM deplocks hit the dedicated llm-lock rule block and also emit
+# python_dependencies so lock updates run the raydepsets --check verification.
+python/deplocks/llm/ray_py311_cpu.lock: llm python_dependencies
+# Raydepsets config changes drive lock regeneration, so they get the same
+# tag set as deplock updates (no macos_wheels).
+ci/raydepsets/configs/ci_core.depsets.yaml: ml tune train serve workflow data core_python dashboard linux_wheels java python_dependencies min_build
+ci/raydepsets/configs/rayimg.depsets.yaml: ml tune train serve workflow data core_python dashboard linux_wheels java python_dependencies min_build
+# Raydepsets tool code changes can alter compiled lock output, so they
+# emit python_dependencies in addition to tools.
+ci/raydepsets/raydepsets.py: tools python_dependencies
+
+# === Buildkite Configs ===
+
+.buildkite/ml.rayci.yml: ml train train_gpu tune
+.buildkite/core.rayci.yml: core_python core_cpp
+.buildkite/others.rayci.yml: java
+.buildkite/lint.rayci.yml: tools
+.buildkite/macos.rayci.yml: macos_wheels
+.buildkite/base.rayci.yml: docker linux_wheels tools
+
+# === Min installation ===
+
+ci/docker/min.build.Dockerfile: min_build
+ci/docker/min.build.wanda.yaml: min_build
+
+# === Java/C++ ===
+
+java/ray.java: java
+cpp/ray.cc: cpp
+src/ray.cpp: core_cpp cpp java core_python linux_wheels macos_wheels dashboard release_tests
+
+# === Docker ===
+
+docker/Dockerfile.ray: docker linux_wheels
+
+# === Documentation ===
+
+doc/code.py: doc
+doc/example.ipynb: doc
+.readthedocs.yaml: doc
+.vale.ini: doc
+.vale/styles/config/vocabularies/Core/accept.txt: doc
+doc/requirements-doc.txt: doc
+python/deplocks/docs/docbuild_depset_py3.10.lock: doc python_dependencies
+ci/raydepsets/configs/docs.depsets.yaml: doc python_dependencies
+
+# === Release ===
+
+release/requirements.txt: release_tests
+release/requirements_py310.txt: tools
+release/release_tests.yaml: tools
+
+# === CI Scripts ===
+
+ci/lint/lint.sh: tools
+ci/ray_ci/tester.py: tools
+ci/ci.sh: tools
+# Windows CI driver scripts trigger the Windows test steps, not just tools.
+ci/ray_ci/windows/build_base.sh: windows tools
+ci/ray_ci/windows/install_tools.sh: windows tools
+
+# === Build Scripts ===
+
+build-wheel.sh: tools
+ci/build/build_common.py: tools
+
+# === Root Files ===
+
+BUILD.bazel: ml tune train data serve core_cpp cpp java core_python doc linux_wheels macos_wheels dashboard tools release_tests

.buildkite/test.rules.txt

@@ -0,0 +1,364 @@
+# Ray CI conditional testing rules definition files
+#
+# Comment content, after '#', will be ignored.
+# Empty lines will be ignored too.
+#
+#   ! tag1 tag2 tag3  # Declares a tag. A tag must be declared first to be used.
+#   # Tags must be declared at the beginning.
+#
+#   dir/  # Directory to match
+#   file  # File to match
+#   dir/*.py  # Pattern to match, using fnmatch, matches dir/a.py dir/dir/b.py or dir/.py
+#   @ tag1 tag2 tag3  # Tags to emit for a rule. A rule without tags is a skipping rule.
+#
+#   ;  # Semicolon to separate rules
+
+! always lint
+! core_python cpp core_cpp java workflow cgraphs_direct_transport dashboard
+! ray_client runtime_env_container
+! data dask serve ml tune train train_gpu llm rllib rllib_gpu rllib_directly
+! linux_wheels macos_wheels docker doc python_dependencies min_build tools windows
+! release_tests spark_on_ray rocksdb_tests redis_tests
+
+# Documentation prose (.md and .rst) does not block premerge. A content-only
+# change to narrative docs triggers no library test steps: prose can't change
+# tested code, and the post-merge documentation build is the coverage for these
+# changes. Executable doc assets such as .py and .ipynb are matched by the rules
+# below and still run tests.
+doc/*.md
+doc/*.rst
+# pass
+;
+
+python/ray/air/
+@ ml train train_gpu tune data linux_wheels
+;
+
+python/deplocks/llm/*.lock
+@ llm python_dependencies
+;
+
+python/ray/llm/
+doc/source/llm/
+doc/source/data/doc_code/working-with-llms/
+ci/docker/llm.build.Dockerfile
+@ llm
+;
+
+python/ray/data/
+ci/docker/data.build.Dockerfile
+ci/docker/data.build.wanda.yaml
+ci/docker/datan.build.wanda.yaml
+ci/docker/data9.build.wanda.yaml
+ci/docker/datal.build.wanda.yaml
+@ data
+;
+
+python/ray/workflow/
+@ workflow
+;
+
+python/ray/tune/
+@ ml train tune linux_wheels
+;
+
+python/ray/train/
+@ ml train train_gpu linux_wheels
+;
+
+ci/docker/ml.build.wanda.yaml
+ci/docker/mllightning2gpu.build.wanda.yaml
+ci/docker/ml.build.Dockerfile
+ci/ray_ci/ml.tests.yml
+@ ml train train_gpu tune
+;
+
+ci/docker/min.build.Dockerfile
+ci/docker/min.build.wanda.yaml
+@ min_build
+;
+
+rllib/
+python/ray/rllib/
+ci/ray_ci/rllib.tests.yml
+@ rllib rllib_gpu rllib_directly
+;
+
+python/ray/serve/
+ci/docker/serve.build.Dockerfile
+@ serve linux_wheels java
+;
+
+python/ray/dashboard/
+@ dashboard linux_wheels core_python
+;
+
+# The macOS smoke test installs this specific lock file
+# (ci/ray_ci/macos/macos_ci.sh), so changes here must still trigger
+# macos_wheels. Must precede the general python/deplocks/ rule below.
+# Also emits python_dependencies so lock file changes still run the
+# raydepsets --check verification in dependencies.rayci.yml.
+python/deplocks/ci/macos_depset_py*
+@ macos_wheels python_dependencies
+;
+
+# Short-circuit deps handling for docs-specific.
+python/deplocks/docs/*.lock
+ci/raydepsets/configs/docs.depsets.yaml
+@ doc python_dependencies
+;
+
+# Raydepsets-generated lock files and raydepsets configs that drive
+# their generation. These do NOT affect the macOS smoke test (which
+# only consumes macos_depset_py*, handled above), so we deliberately
+# omit macos_wheels here to avoid running mac tests on unrelated lock
+# updates. Otherwise mirrors the python/setup.py rule's tag set so
+# general dependency changes still fan out across CI.
+python/deplocks/
+ci/raydepsets/configs/
+@ ml tune train serve workflow data min_build
+@ core_python dashboard linux_wheels java
+@ python_dependencies
+;
+
+python/setup.py
+python/requirements.txt
+python/requirements_compiled.txt
+python/requirements_compiled_py*
+python/requirements/
+@ ml tune train serve workflow data min_build
+@ core_python dashboard linux_wheels macos_wheels java
+@ python_dependencies
+;
+
+# Things that need to execute on GPU's
+python/ray/dag/
+python/ray/experimental/channel/
+python/ray/experimental/rdt/
+python/ray/experimental/collective/
+python/ray/tests/rdt/
+python/ray/dashboard/modules/reporter/gpu_providers.py
+python/ray/tests/test_gpu_provider_on_gpu.py
+@ core_python cgraphs_direct_transport
+;
+
+python/ray/util/client/
+@ core_python ray_client
+;
+
+python/ray/util/dask/
+@ core_python dask
+;
+
+python/ray/util/spark/
+@ core_python spark_on_ray
+;
+
+python/ray/runtime_env/
+@ core_python runtime_env_container
+;
+
+python/
+# Run library tests on core Python code change.
+@ core_python llm ml tune train data serve
+# Python changes might impact cross language stack in Java.
+# Java also depends on Python CLI to manage processes.
+@ core_python dashboard linux_wheels macos_wheels java
+;
+
+.buildkite/core.rayci.yml
+@ core_python core_cpp
+;
+
+java/
+@ java
+;
+
+cpp/
+@ cpp
+;
+
+docker/
+.buildkite/pipeline.build_cpp.yml
+.buildkite/_images.rayci.yml
+.buildkite/release/_images.rayci.yml
+@ docker linux_wheels
+;
+
+.readthedocs.yaml
+@ doc
+;
+
+doc/*.py
+doc/*.ipynb
+doc/BUILD
+doc/*/BUILD
+doc/*.rst
+doc/requirements-doc.txt
+.vale.ini
+.vale/
+.buildkite/doc.rayci.yml
+@ doc
+;
+
+ci/docker/doctest.build.Dockerfile
+ci/docker/doctest.build.wanda.yaml
+# pass
+;
+
+release/ray_release/
+release/requirements_*
+release/*.md
+release/*.yaml
+@ tools
+;
+
+release/
+@ release_tests
+;
+
+doc/
+examples/
+dev/
+kubernetes/
+site/
+# pass
+;
+
+ci/lint/
+.buildkite/cicd.rayci.yml
+.buildkite/lint.rayci.yml
+.buildkite/bisect/
+ci/fossa/
+ci/docker/fossa.Dockerfile
+ci/docker/fossa.wanda.yaml
+bazel/tests/
+@ tools
+;
+
+# Raydepsets tool code. Changes here can alter what gets compiled into
+# lock files, so emit python_dependencies to re-run the compile/check.
+# The configs/ subdir is handled earlier with the deplock rule block.
+ci/raydepsets/
+@ tools python_dependencies
+;
+
+.buildkite/macos.rayci.yml
+.buildkite/pipeline.macos.yml
+ci/ray_ci/macos/macos_ci.sh
+ci/ray_ci/macos/macos_ci_build.sh
+@ macos_wheels
+;
+
+# Windows CI driver scripts (base image build, tool install, cleanup) feed the
+# windowsbuild image that every Windows test consumes. Emit 'windows' so the
+# Windows test steps (tagged 'windows') run, not just the image rebuild. Must
+# precede the general ci/ray_ci/ rule below, which would otherwise swallow
+# these into 'tools' only.
+ci/ray_ci/windows/
+@ windows tools
+;
+
+ci/pipeline/
+ci/build/
+ci/ray_ci/
+.buildkite/_forge.rayci.yml
+.buildkite/_forge.aarch64.rayci.yml
+ci/docker/forge.wanda.yaml
+ci/docker/forge.aarch64.wanda.yaml
+.buildkite/pipeline.build.yml
+.buildkite/hooks/post-command
+.buildkite/release/
+.buildkite/release-automation/
+build-wheel.sh
+build-image.sh
+@ tools
+;
+
+.buildkite/base.rayci.yml
+.buildkite/build.rayci.yml
+.buildkite/pipeline.arm64.yml
+ci/docker/manylinux.Dockerfile
+ci/docker/manylinux.wanda.yaml
+ci/docker/manylinux.aarch64.wanda.yaml
+ci/docker/windows.build.Dockerfile
+ci/docker/windows.build.wanda.yaml
+build-docker.sh
+@ docker linux_wheels tools
+;
+
+ci/run/
+ci/ci.sh
+.buildkite/*.rules.test.txt
+.buildkite/*.rules.txt
+@ tools
+;
+
+# Per-library pipeline definition files trigger only that library's suite,
+# instead of falling through to the wildcard '*' below (which would fan out to
+# the full library suite). These must stay after the specific '.buildkite/...'
+# rules above (core/doc/lint/macos/base/*.rules.txt) and before the final '*';
+# the generic '.buildkite/*.rayci.yml' fallback must come last so the
+# per-library rules win.
+.buildkite/data.rayci.yml
+@ data
+;
+
+.buildkite/serve.rayci.yml
+@ serve linux_wheels java
+;
+
+.buildkite/ml.rayci.yml
+@ ml train train_gpu tune
+;
+
+.buildkite/llm.rayci.yml
+@ llm
+;
+
+.buildkite/*.rayci.yml
+@ java
+;
+
+src/ray/core_worker/experimental*.h
+src/ray/core_worker/experimental*.cc
+@ cgraphs_direct_transport
+;
+
+# REP-64: changes to the GCS store_client API or backend implementations
+# (rocksdb, redis, in-memory) must re-run the GCS FT premerge suites for
+# both backends. Also covers rocksdb build-flag changes. The broader
+# `core_cpp ...` tags below mirror the catch-all `src/` rule so this
+# path keeps its normal build coverage on top of the FT suites.
+src/ray/gcs/store_client/
+bazel/rocksdb.BUILD
+@ rocksdb_tests redis_tests
+@ core_cpp cpp java core_python linux_wheels macos_wheels dashboard release_tests
+;
+
+src/
+@ core_cpp cpp
+@ java core_python linux_wheels macos_wheels
+@ dashboard release_tests
+;
+
+.github/
+README.rst
+SECURITY.md
+CONTRIBUTING.rst
+LICENSE
+pylintrc
+semgrep.yml
+setup_hooks.sh
+.pre-commit-config.yaml
+.isort.cfg
+.prettierrc.toml
+.fossa.yml
+# pass
+;
+
+*
+@ ml tune train data serve
+@ core_cpp cpp java core_python doc
+@ linux_wheels macos_wheels dashboard tools release_tests
+;

.buildkite/windows.rayci.yml

@@ -0,0 +1,199 @@
+group: windows tests
+sort_key: "~windows"
+steps:
+  - name: windowsbuild
+    wanda: ci/docker/windows.build.wanda.yaml
+    instance_type: builder-windows
+
+  - label: ":ray: core: :windows: smoke test"
+    if: build.env("BUILDKITE_PIPELINE_ID") == "0189942e-0876-4b8f-80a4-617f988ec59b" || build.env("BUILDKITE_PIPELINE_ID") == "018f4f1e-1b73-4906-9802-92422e3badaa"
+    tags:
+      - core_cpp
+      - windows
+    job_env: WINDOWS
+    instance_type: windows
+    commands:
+      - bash ci/ray_ci/windows/install_tools.sh
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests:test_basic core
+        --build-name windowsbuild
+        --operating-system windows
+        --except-tags no_windows
+        --test-env=CI="1"
+        --test-env=USERPROFILE
+    depends_on: windowsbuild
+
+  # block full test suite on premerge and microcheck
+  - block: "run windows tests"
+    key: block-windows-tests
+    if: build.env("BUILDKITE_PIPELINE_ID") == "0189942e-0876-4b8f-80a4-617f988ec59b" || build.env("BUILDKITE_PIPELINE_ID") == "018f4f1e-1b73-4906-9802-92422e3badaa"
+    depends_on: []
+
+  - label: ":windows: wheel {{matrix}}"
+    # we have linux/mac wheels tag, but do not have a windows wheels tag..
+    # so using python and core_cpp here, to make sure at least it builds
+    key: windows_wheels
+    tags:
+      - oss
+      - core_python
+      - core_cpp
+      - release_wheels
+    job_env: WINDOWS
+    instance_type: windows
+    commands:
+      - bash ci/ray_ci/windows/install_tools.sh
+      - bazel run //ci/ray_ci:build_in_docker_windows -- wheel --python-version {{matrix}} --operating-system windows --upload
+    matrix:
+      - "3.10"
+      - "3.11"
+      - "3.12"
+    depends_on:
+      - windowsbuild
+      - block-windows-tests
+
+  - label: ":ray: core: :windows: cpp tests"
+    tags:
+      - core_cpp
+      - windows
+    job_env: WINDOWS
+    instance_type: windows
+    commands:
+      - bash ci/ray_ci/windows/install_tools.sh
+      - bazel run //ci/ray_ci:test_in_docker -- //:all //src/... core
+        --build-name windowsbuild
+        --operating-system windows
+        --except-tags no_windows,cgroup
+        --test-env=CI="1"
+        --test-env=RAY_CI_POST_WHEEL_TESTS="1"
+        --test-env=USERPROFILE
+        --parallelism-per-worker 2
+    depends_on:
+      - windowsbuild
+      - block-windows-tests
+
+  - label: ":ray: core: :windows: python tests"
+    tags:
+      - core_python
+      - windows
+    job_env: WINDOWS
+    instance_type: windows
+    parallelism: 5
+    commands:
+      - bash ci/ray_ci/windows/install_tools.sh
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/tests/... core
+        --build-name windowsbuild
+        --operating-system windows
+        --except-tags no_windows
+        --test-env=CI="1"
+        --test-env=RAY_CI_POST_WHEEL_TESTS="1"
+        --test-env=USERPROFILE
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 2
+    depends_on:
+      - windowsbuild
+      - block-windows-tests
+
+  - label: ":ray-serve: serve: :windows: tests"
+    tags:
+      - serve
+      - windows
+    job_env: WINDOWS
+    instance_type: windows
+    parallelism: 2
+    commands:
+      - bash ci/ray_ci/windows/install_tools.sh
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/serve/... serve
+        --build-name windowsbuild
+        --operating-system windows
+        --except-tags no_windows,use_all_core_windows
+        --test-env=CI="1"
+        --test-env=RAY_CI_POST_WHEEL_TESTS="1"
+        --test-env=USERPROFILE
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 1
+    depends_on:
+      - windowsbuild
+      - block-windows-tests
+
+  - label: ":ray-serve: serve: :windows: enormous tests"
+    tags:
+      - serve
+      - windows
+    job_env: WINDOWS
+    instance_type: windows
+    commands:
+      - bash ci/ray_ci/windows/install_tools.sh
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/serve/... serve
+        --build-name windowsbuild
+        --operating-system windows
+        --only-tags use_all_core_windows
+        --except-tags no_windows
+        --test-env=CI="1"
+        --test-env=RAY_CI_POST_WHEEL_TESTS="1"
+        --test-env=USERPROFILE
+    depends_on:
+      - windowsbuild
+      - block-windows-tests
+
+  - label: ":train: ml: :windows: tests"
+    tags:
+      - train
+      - windows
+    job_env: WINDOWS
+    instance_type: windows
+    commands:
+      - bash ci/ray_ci/windows/install_tools.sh
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/train:test_windows ml
+        --build-name windowsbuild
+        --operating-system windows
+        --test-env=CI="1"
+        --test-env=RAY_CI_POST_WHEEL_TESTS="1"
+        --test-env=USERPROFILE
+    depends_on:
+      - windowsbuild
+      - block-windows-tests
+
+  - label: "flaky :windows: core tests"
+    key: windows_core_flaky_tests
+    tags:
+      - flaky
+      - windows
+      - skip-on-premerge
+    job_env: WINDOWS
+    instance_type: windows
+    parallelism: 2
+    commands:
+      - bash ci/ray_ci/windows/install_tools.sh
+      - bazel run //ci/ray_ci:test_in_docker -- //:all //src/... //python/ray/tests/... core
+        --run-flaky-tests
+        --except-tags no_windows
+        --build-name windowsbuild
+        --operating-system windows
+        --test-env=CI="1"
+        --test-env=RAY_CI_POST_WHEEL_TESTS="1"
+        --test-env=USERPROFILE
+        --workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}"
+    depends_on:
+      - windowsbuild
+      - block-windows-tests
+    soft_fail: true
+
+  - label: "flaky :windows: serve tests"
+    key: windows_serve_flaky_tests
+    tags:
+      - flaky
+      - windows
+      - skip-on-premerge
+    job_env: WINDOWS
+    instance_type: windows
+    commands:
+      - bash ci/ray_ci/windows/install_tools.sh
+      - bazel run //ci/ray_ci:test_in_docker -- //python/ray/serve/... serve
+        --except-tags no_windows
+        --run-flaky-tests
+        --build-name windowsbuild
+        --operating-system windows
+        --test-env=CI="1"
+        --test-env=RAY_CI_POST_WHEEL_TESTS="1"
+        --test-env=USERPROFILE
+    depends_on:
+      - windowsbuild
+      - block-windows-tests
+    soft_fail: true

.clang-format

@@ -0,0 +1,7 @@
+BasedOnStyle: Google
+ColumnLimit: 90
+DerivePointerAlignment: false
+IndentCaseLabels: false
+PointerAlignment: Right
+BinPackArguments: false
+BinPackParameters: false

.clang-tidy

@@ -0,0 +1,86 @@
+# Disable the following checks with reasons in parenthesis:
+#
+# -bugprone-macro-parentheses (inconsistent style)
+# -google-readability-todo (potentially too restrictive)
+# -misc-non-private-member-variables-in-classes (potentially too restrictive)
+# -misc-unused-parameters (can be cleaned up in batch and enabled)
+# -modernize-avoid-c-arrays (too restrictive)
+# -modernize-concat-nested-namespaces (inconsistent style)
+# -modernize-pass-by-value (too restrictive)
+# -modernize-return-braced-init-list (inconsistent style)
+# -modernize-use-emplace (more subtle behavior)
+# -modernize-use-nodiscard (too much noise)
+# -modernize-use-trailing-return-type (inconsistent style)
+# -modernize-use-override (TODO(mwtian): re-enable after fixing existing derived classes)
+# -modernize-avoid-bind (incorrect conversion)
+# -modernize-loop-convert (more subtle behavior)
+# -modernize-replace-disallow-copy-and-assign-macro (inconsistent style)
+# -modernize-make-unique (doesn't work with private constructor)
+# -modernize-make-shared (doesn't work with private constructor)
+# Other readability-* rules (potentially too noisy, inconsistent style)
+# Other rules not mentioned here or below (not yet evaluated)
+#
+# TODO: enable google-* and readability-* families of checks.
+Checks: >
+  abseil-*,
+  bugprone-*,
+  -bugprone-macro-parentheses,
+  -bugprone-easily-swappable-parameters,
+  -bugprone-narrowing-conversions,
+  -bugprone-implicit-widening-of-multiplication-result,
+  cert-*,
+  cppcoreguidelines-*,
+  -cppcoreguidelines-non-private-member-variables-in-classes,
+  -cppcoreguidelines-narrowing-conversions,
+  -cppcoreguidelines-avoid-magic-numbers,
+  -cppcoreguidelines-avoid-do-while,
+  google-*,
+  -google-readability-todo,
+  -google-default-arguments,
+  misc-*,
+  -misc-non-private-member-variables-in-classes,
+  -misc-unused-parameters,
+  -misc-include-cleaner,
+  -misc-const-correctness,
+  modernize-*,
+  -modernize-concat-nested-namespaces,
+  -modernize-return-braced-init-list,
+  -modernize-use-nodiscard,
+  -modernize-use-trailing-return-type,
+  -modernize-avoid-bind,
+  -modernize-loop-convert,
+  performance-*,
+  readability-braces-around-statements,
+  readability-const-return-type,
+  readability-container-contains,
+  readability-container-data-pointer,
+  readability-container-size-empty,
+  readability-delete-null-pointer,
+  readability-duplicate-include,
+  readability-implicit-bool-conversion,
+  readability-make-member-function-const,
+  readability-misleading-indentation,
+  readability-misplaced-array-index,
+  readability-named-parameter,
+  readability-non-const-parameter,
+  readability-redundant-*,
+  -readability-redundant-access-specifiers,
+  readability-static-definition-in-anonymous-namespace,
+  readability-string-compare,
+  readability-suspicious-call-argument,
+
+CheckOptions:
+  # Reduce noisiness of the bugprone-narrowing-conversions check.
+  - key:   bugprone-narrowing-conversions.IgnoreConversionFromTypes
+    value: 'size_t;ptrdiff_t;size_type;difference_type'
+  - key:   bugprone-narrowing-conversions.WarnOnEquivalentBitWidth
+    value: 'false'
+  - key: cppcoreguidelines-special-member-functions.AllowMissingMoveFunctionsWhenCopyIsDeleted
+    value: 'true'
+  - key: cppcoreguidelines-special-member-functions.AllowSoleDefaultDtor
+    value: 'true'
+  - key: performance-move-const-arg.CheckTriviallyCopyableMove
+    value: 'false'
+
+# Turn all the warnings from the checks above into errors.
+WarningsAsErrors: "*"

.claude/CLAUDE.md

@@ -0,0 +1,33 @@
+<!-- Version-controlled. Personal config → CLAUDE.local.md -->
+<!-- Library-specific guidance → each library's .claude/CLAUDE.md -->
+
+# Ray
+
+Ray is a unified framework for scaling AI and Python applications.
+
+## Building & Linting
+
+Refer to doc/source/ray-contribute/development.md for the most up-to date information.
+Use the /rebuild skill for guided rebuilds and the /lint skill for linting.
+
+## Testing
+
+See per-library .claude/CLAUDE.md for library-specific test paths.
+Default test timeout: 180s (pytest.ini).
+
+## Structure
+
+- src/ray/ — C++ core runtime
+- python/ray/ — Python API and AI libraries (data, serve, train, tune)
+- rllib/ — RLlib (symlinked from python/ray/rllib)
+- doc/source/ — Sphinx documentation
+
+## Development Workflow
+
+- After making C++ or Cython changes, use /rebuild to determine the correct build steps
+- After making code changes, use /lint to fix lint issues on modified files
+- When investigating CI failures, use /fetch-buildkite-logs to fetch and analyze build logs
+
+## Contributing
+
+See @CONTRIBUTING.rst and @doc/source/ray-contribute/getting-involved.md

.claude/agents/README.md

@@ -0,0 +1,4 @@
+<!-- Project-specific Claude Code subagents. -->
+<!-- See https://code.claude.com/docs/en/sub-agents -->
+<!-- To create: .claude/agents/<name>/<name>.md -->
+<!-- Example use cases: docs specialist, security reviewer -->

.claude/rules/python-guidelines.md

@@ -0,0 +1,10 @@
+---
+paths:
+  - "**/*.py"
+---
+<!-- Python coding guidelines — derived from docs.ray.io/en/master/ray-contribute/getting-involved.html -->
+<!-- Source of truth: doc/source/ray-contribute/getting-involved.md "Code Style" section -->
+- Place type annotations in function signatures so tooling (mypy, pyright) can use them directly
+- Use @pytest.mark.parametrize to cover multiple cases in a single test function, reducing duplication
+- Extract common test setup/teardown into reusable helper functions
+- Use @classmethod setUpClass/tearDownClass to reuse Ray clusters across test suites (avoids ~4.4s startup per test)

.claude/rules/security.md

@@ -0,0 +1,3 @@
+<!-- Security rules applying to all code -->
+- Add token-based authentication to all new gRPC endpoints and RPC handlers to maintain Ray's security model
+- Propagate auth tokens in new API calls (both C++ and Python sides) so that end-to-end authentication remains consistent

.claude/rules/timing.md

@@ -0,0 +1,9 @@
+---
+paths:
+  - "src/**/*.{cc,h}"
+---
+
+- Excluding the Clock implementation and benchmarks, read the current time only through an injected `ray::ClockInterface` (`src/ray/util/clock.h`) so time can be faked and unit tested deterministically. Do not call `absl::Now()`, `std::chrono::{system,steady,high_resolution}_clock::now()`, or other similar functions.
+- Inject `ClockInterface &clock_` via the constructor. Pass a `Clock` from the production entrypoint (e.g. `raylet/main.cc`) and a `FakeClock` in tests. Declare the concrete clock member before any object that holds a `ClockInterface &` so it is constructed first and outlives the holder.
+- Use `clock_.Now()` / `clock_.NowUnixMillis()` for wall-clock timestamps and deadlines, and `clock_.SteadyNow()` for elapsed/duration measurements
+- In unit tests use `FakeClock::AdvanceTime`/`SetTime` instead of `sleep` or wall-clock time. Ensure that the tests are written to be fast and deterministic.

.claude/settings.json

@@ -0,0 +1,18 @@
+{
+  "permissions": {
+    "allow": [
+      "Bash(bazel build *)",
+      "Bash(bazel test *)",
+      "Bash(bazel run *)",
+      "Bash(bazel query *)",
+      "Bash(bazel info *)",
+      "Bash(python -m pytest *)",
+      "Bash(pip install -e *)",
+      "Bash(git status)",
+      "Bash(git diff *)",
+      "Bash(git log *)",
+      "Bash(git branch *)"
+    ],
+    "deny": []
+  }
+}

.claude/skills/fetch-buildkite-logs/SKILL.md

@@ -0,0 +1,54 @@
+---
+name: fetch-buildkite-logs
+description: Fetch and analyze Buildkite CI build logs for failures
+---
+
+# Fetch Buildkite Logs
+
+## Prerequisites
+- `BUILDKITE_API_TOKEN` must be set in the environment (typically `~/.bashrc`)
+- If not configured, direct user to `doc/source/ray-contribute/agent-development.md` for setup
+
+## Parsing the Buildkite URL
+
+A Buildkite URL has the form:
+
+```
+https://buildkite.com/ray-project/<PIPELINE>/builds/<BUILD_NUM>#<JOB_ID>
+```
+
+Always extract `<PIPELINE>` (e.g. `premerge`, `postmerge`) and `<BUILD_NUM>` from the URL the user provides. **Do not hardcode `premerge`** — the same skill is used for all pipelines. If a `#<JOB_ID>` fragment is present, it identifies a specific real job (not a group/wait job) and can be queried directly.
+
+## Steps
+
+1. Verify token: `echo $BUILDKITE_API_TOKEN | head -c4`
+2. If token missing, stop and show setup instructions from the dev docs
+3. Fetch build (use the pipeline from the URL):
+   ```bash
+   curl -s -H "Authorization: Bearer $BUILDKITE_API_TOKEN" \
+     "https://api.buildkite.com/v2/organizations/ray-project/pipelines/<PIPELINE>/builds/<BUILD_NUM>"
+   ```
+4. If a job ID is present in the URL fragment, look it up directly:
+   ```bash
+   curl -s -H "Authorization: Bearer $BUILDKITE_API_TOKEN" \
+     "https://api.buildkite.com/v2/organizations/ray-project/pipelines/<PIPELINE>/builds/<BUILD_NUM>" \
+     | python3 -c "import sys,json; jobs=json.load(sys.stdin)['jobs']; [print(f\"{j['id']} {j.get('name')} -> {j.get('state')}\") for j in jobs if j['id']=='<JOB_ID>']"
+   ```
+5. Otherwise list failed/broken jobs:
+   ```bash
+   curl -s -H "Authorization: Bearer $BUILDKITE_API_TOKEN" \
+     "https://api.buildkite.com/v2/organizations/ray-project/pipelines/<PIPELINE>/builds/<BUILD_NUM>" \
+     | python3 -c "import sys,json; jobs=json.load(sys.stdin)['jobs']; [print(f\"{j['id']} {j['name']} -> {j['state']}\") for j in jobs if j.get('state') in ('failed','broken')]"
+   ```
+6. Fetch individual job log:
+   ```bash
+   curl -s -H "Authorization: Bearer $BUILDKITE_API_TOKEN" \
+     "https://api.buildkite.com/v2/organizations/ray-project/pipelines/<PIPELINE>/builds/<BUILD_NUM>/jobs/<JOB_ID>/log" \
+     > /tmp/log_<JOB_ID>.json
+   ```
+   Logs come back as JSON with a `content` field containing ANSI escape codes — strip them with `re.sub(r'\x1b\[[0-9;]*m', '', content)` before grepping.
+7. Summarize failures and suggest fixes.
+
+## Authentication note
+
+If `curl` returns `{"message":"No organization found"}`, the configured token does not have access to `ray-project`. The user may have a separate org-scoped token — ask them which env var to source.

.claude/skills/lint/SKILL.md

@@ -0,0 +1,43 @@
+---
+name: lint
+description: Run linting and formatting checks on Ray code
+---
+
+# Lint Modified Files
+
+Run pre-commit on the files you changed:
+
+```bash
+pre-commit run --files $(git diff --name-only HEAD)
+```
+
+`pre-commit run` without `--files` only operates on staged files, so pass the
+modified file list explicitly.
+
+If pre-commit is not installed:
+```bash
+pip install -c python/requirements_compiled.txt pre-commit && pre-commit install
+```
+
+## Handling remaining errors
+
+Pre-commit auto-fixes simple issues (formatting, long lines, unused imports).
+Review any remaining errors — these typically need code changes such as adding a
+missing import, resolving a name conflict, or restructuring logic. Fix them by
+editing the source code directly.
+
+Use `# noqa` only for false positives that cannot be resolved by changing the code,
+and include the rule code and reason: `# noqa: E501 — URL cannot be split`.
+
+## Exclusions
+
+pyproject.toml lists files in `per-file-ignores` and `extend-exclude`. When the PR
+modifies a file that is on one of these lists, fix the lint issues in your changes
+and consider removing the file from the list. Leave exclusion entries for files
+outside the PR scope untouched.
+
+## Reference
+
+- Hook config: .pre-commit-config.yaml
+- Ruff config: pyproject.toml (`[tool.ruff]` section)
+- Docs: doc/source/ray-contribute/development.md ("Development tooling")

.claude/skills/ray-dependencies/SKILL.md

@@ -0,0 +1,433 @@
+---
+name: ray-dependencies
+description: Manage Python dependencies in Ray — add/remove/upgrade packages, work with raydepsets lock files, debug dependency conflicts, and regenerate compiled requirements. Covers `python/requirements*`, `python/requirements/**`, `python/deplocks/**`, and `ci/raydepsets/configs/*.depsets.yaml`.
+user-invocable: true
+argument-hint: <question or task>
+---
+
+# Ray Dependencies
+
+Expert skill for managing Python dependencies across the Ray repository: the monorepo `requirements_compiled*.txt` lock files, the raydepsets DAG-based lock file manager, modular `python/requirements/**` source files, and Docker image dependency chains.
+
+---
+
+## When to use this skill
+
+**Use this skill when the user wants to:**
+
+- Add, remove, or upgrade a Python dependency in Ray
+- Create or modify a `.depsets.yaml` config file
+- Understand how dependencies flow between Ray Docker images
+- Debug dependency conflicts or version resolution failures
+- Regenerate lock files after requirement changes
+- Create a new CI test environment with locked dependencies
+- Understand why a specific package version was chosen
+
+**Not for:**
+
+- General Python packaging questions unrelated to Ray
+- Ray runtime/API questions (use Ray docs)
+- Docker image build issues unrelated to dependencies
+
+---
+
+## Workflow rules (project preferences)
+
+These take precedence over generic packaging advice:
+
+1. **Source-file pins only.** Resolve conflicts by editing `python/requirements.txt`, `python/requirements/**/*.txt`, or `python/requirements/**/*.in`. Do **not** hand-edit `python/requirements_compiled*.txt` — it is a build artifact and gets overwritten on the next compile.
+2. **No `ci/ci.sh` post-process hooks** for individual package fixes. Only touch `ci/ci.sh` for genuinely structural changes (new functions, new input files passed to the compiler). Never as an after-the-fact lock mutator.
+3. **Use the dual-exact-pin-with-markers pattern** when a package needs different versions on different Python versions and the lock is consumed as a constraint across multiple Python targets. See *Marker preservation* below.
+4. **`python/requirements.txt` ↔ `python/setup.py` must stay in sync.** The packages under the `## setup.py install_requires` block in `python/requirements.txt` are mirrored into `setup_spec.install_requires` in `python/setup.py` (around line 405). When you add, remove, or change a version bound for any package in that block, edit **both** files in the same change. The list in `setup.py` is what end users actually install via `pip install ray`; `requirements.txt` is the dev-side source of truth. Drift between them ships broken installs.
+5. **`python/requirements/llm/llm-requirements.txt` ↔ `setup_spec.extras["llm"]` must stay in sync.** The `ray[llm]` extra in `python/setup.py` (around line 377) and `python/requirements/llm/llm-requirements.txt` are paired source-of-truth files for the LLM install set — both have explicit "keep in sync" comments. When you add, remove, or change a permanent version bound for any package in the LLM extra, edit **both** files. **Exception:** temporary upper-bound workaround pins (`<=X.Y.Z` to dodge a bug) may live only in `llm-requirements.txt`. They must NOT be added to `setup.py`, since `setup.py` is the public install constraint and should not advertise short-lived workarounds as future API. Strip the `<=` pin from both files once the upstream fix lands.
+6. **When presenting options, list source-file fixes first.** Mention lock or `ci.sh` edits only as fallbacks with downsides called out.
+
+---
+
+## Ray Dependency Architecture
+
+Ray uses a two-tier dependency management system:
+
+1. **`requirements_compiled*.txt`** — monorepo-wide pinned dependency files, compiled via `ci/ci.sh compile_pip_dependencies`. One per Python version: `requirements_compiled.txt` (default), `requirements_compiled_py3.10.txt`, `requirements_compiled_py3.11.txt`, etc.
+2. **raydepsets** — a DAG-based lock file manager (`ci/raydepsets/`) that generates per-image, per-environment lock files from `.depsets.yaml` configs. Lock files live in `python/deplocks/` and `release/ray_release/byod/`.
+
+### Key file locations
+
+| Path | Purpose |
+|---|---|
+| `python/requirements.txt` | Base Ray installation requirements |
+| `python/requirements_compiled.txt` | Monorepo pinned dependencies (per-Python-version variants exist) |
+| `python/requirements/` | Modular requirement files by component (test, ml, data, train, tune, serve, rllib, llm) |
+| `python/requirements/ml/py313/` | ML requirements organized by Python version |
+| `python/requirements/data/` | Ray Data variant requirements (pyarrow versions, mongo, etc.) |
+| `python/requirements/llm/` | LLM requirements (`llm-requirements.txt`, `llm-test-requirements.txt`) |
+| `python/requirements/serve/` | Serve requirements and overrides |
+| `python/deplocks/` | Generated lock files (output of raydepsets) |
+| `docker/base-deps/requirements.in` | Docker base-deps layer requirements |
+| `docker/base-extra/requirements.in` | Docker base-extra layer requirements |
+| `docker/base-slim/requirements.in` | Docker slim image requirements |
+| `release/ray_release/byod/` | BYOD (Bring Your Own Dependencies) files for release tests |
+
+---
+
+## Generating the constraints (`requirements_compiled*.txt`)
+
+The two compiled lock files are produced by two `bash` functions in `ci/ci.sh`:
+
+| Function | Output | Source set |
+|---|---|---|
+| `compile_pip_dependencies` (`ci/ci.sh:16`) | `python/requirements_compiled.txt` | shared `python/requirements/**` files (test, cloud, docker, `ml/*`, security) |
+| `compile_313_pip_dependencies` (`ci/ci.sh:82`) | `python/requirements_compiled_py3.13.txt` | py313 overrides under `python/requirements/py313/**` and `python/requirements/ml/py313/**`, falling back to shared files |
+
+### How to invoke
+
+```bash
+# Default-Python lock (currently py3.10/3.11/3.12 generic)
+ci/ci.sh compile_pip_dependencies
+
+# py3.13 lock (uses py313 override directories)
+ci/ci.sh compile_313_pip_dependencies
+
+# Custom output filename (rare)
+ci/ci.sh compile_pip_dependencies my_custom_lock.txt
+```
+
+Run inside an environment matching the target Python version (the function `pip install`s `pip-tools==7.4.1` and `wheel==0.45.1` itself). aarch64/arm64 is a no-op — the function returns early because not all pinned packages have aarch64 wheels.
+
+### What it does
+
+Both functions wrap `pip-compile` (pip-tools 7.4.1) with the same flags:
+
+```
+pip-compile --verbose --resolver=backtracking \
+  --pip-args --no-deps --strip-extras --no-header \
+  --unsafe-package ray --unsafe-package pip --unsafe-package setuptools \
+  -o "python/$TARGET" \
+  <list of source requirement files>
+```
+
+Then two post-process `sed` passes on the output:
+1. `sed -i "/@ file/d"` — strips local file:// install lines.
+2. `sed -i -E 's/==([\.0-9]+)\+[^\b]*cpu/==\1/g'` — strips `+cpu` / `+pt20cpu` device-tag suffixes that the resolver inserts (otherwise `pip install` later complains about irresolvable constraints).
+
+The function `pip install`s `numpy` and `torch` before compilation. **Why:** `pip-compile` runs with `--pip-args --no-deps`, but it still has to extract each candidate's own `install_requires` to feed the resolver. For legacy sdists (no wheel, no PEP 517 `pyproject.toml`), the only way to get metadata is to execute `setup.py egg_info` — which runs the package's `setup.py` as Python. If that `setup.py` does `import numpy` / `import torch` at module level (common for packages using `numpy.distutils` or `torch.utils.cpp_extension` for C-extension config), the import has to succeed or pip-compile aborts. pip-compile doesn't sandbox these in an isolated PEP 517 build env, so the calling Python must already have those modules installed. `dragonfly-opt` was the canonical offender (no longer in the tree); the preinstall stays because the same shape of failure recurs whenever a new sdist-only dep with imperative `setup.py` imports gets added.
+
+### Source file lists
+
+If you add a brand-new source requirement file under `python/requirements/**`, it will NOT be picked up automatically — you must extend the `pip-compile` source list inside the relevant function in `ci/ci.sh`. This is one of the few legitimate reasons to edit `ci/ci.sh` (see workflow rule 2). Update both `compile_pip_dependencies` and `compile_313_pip_dependencies` if the new file applies to both Python tracks; if py3.13 needs an override, place it under `python/requirements/py313/` or `python/requirements/ml/py313/` and reference the override in `compile_313_pip_dependencies` only.
+
+### Recompile + relock everything
+
+After editing source requirements, the full refresh is:
+
+```bash
+ci/ci.sh compile_pip_dependencies && \
+ci/ci.sh compile_313_pip_dependencies && \
+bazelisk run //ci/raydepsets:raydepsets -- build --all-configs
+```
+
+The compiled `requirements_compiled*.txt` files feed raydepsets as constraints (via the `remove-compiled-headers.sh` pre-hook, which copies them to `/tmp/ray-deps/` with GPU index URLs stripped).
+
+---
+
+## raydepsets System
+
+### What it does
+
+raydepsets models relationships between lock files as a directed acyclic graph (DAG), so when a dependency changes, downstream lock files regenerate in the correct order. It wraps `uv pip compile` with cross-file consistency guarantees.
+
+### Architecture
+
+```
+YAML configs --> Config parser (workspace.py) --> Template expansion --> DAG (NetworkX DiGraph) --> Topological execution --> uv pip compile --> Lock files
+```
+
+**Source files:**
+- `ci/raydepsets/raydepsets.py` — entry point
+- `ci/raydepsets/cli.py` — CLI (`build` command) and `DependencySetManager` class
+- `ci/raydepsets/workspace.py` — config parsing, `Depset` dataclass, `Workspace` class, template substitution
+
+### Four operations
+
+#### 1. `compile`
+Runs `uv pip compile` to resolve dependencies from `.in`/`.txt` requirement files into a hash-verified lock file.
+
+**Fields:** `requirements` (input files), `constraints` (version constraint files), `packages` (inline package specs via stdin), `output` (lock file path)
+
+```yaml
+- name: ray_img_depset_${PYTHON_SHORT}
+  operation: compile
+  requirements:
+    - python/deplocks/ray_img/ray_dev.in
+  constraints:
+    - /tmp/ray-deps/requirements_compiled_py${PYTHON_VERSION}.txt
+  output: python/deplocks/ray_img/ray_img_py${PYTHON_SHORT}.lock
+  append_flags:
+    - --python-version=${PYTHON_VERSION}
+    - --unsafe-package ray
+    - --python-platform=linux
+  build_arg_sets: [py310, py311, py312, py313]
+  pre_hooks:
+    - ci/raydepsets/pre_hooks/build-placeholder-wheel.sh
+    - ci/raydepsets/pre_hooks/remove-compiled-headers.sh ${PYTHON_VERSION}
+```
+
+#### 2. `subset`
+Extracts a subset of already-resolved packages from another depset's lock file. Validates all requested requirements exist in the source.
+
+**Fields:** `source_depset`, `requirements`, `output`
+
+```yaml
+- name: ray_base_deps_${PYTHON_SHORT}
+  operation: subset
+  source_depset: ray_base_extra_testdeps_${PYTHON_SHORT}
+  requirements:
+    - docker/base-deps/requirements.in
+  output: python/deplocks/base_deps/ray_base_deps_py${PYTHON_VERSION}.lock
+```
+
+#### 3. `expand`
+Combines multiple depsets into one, optionally adding new requirements. Recursively collects all transitive requirements from referenced depsets and recompiles.
+
+**Fields:** `depsets` (depset names to combine), `requirements`, `constraints`, `output`
+
+```yaml
+- name: compiled_ray_llm_test_depset_${PYTHON_VERSION}_${CUDA_CODE}
+  operation: expand
+  depsets:
+    - ray_base_test_depset_${PYTHON_VERSION}_${CUDA_CODE}
+  requirements:
+    - python/requirements/llm/llm-requirements.txt
+    - python/requirements/llm/llm-test-requirements.txt
+  constraints:
+    - python/deplocks/llm/ray_test_${PYTHON_VERSION}_${CUDA_CODE}.lock
+  output: python/deplocks/llm/rayllm_test_${PYTHON_VERSION}_${CUDA_CODE}.lock
+```
+
+#### 4. `relax`
+Removes specified packages from another depset's lock file. Does NOT re-resolve — simple removal. Use with caution; can create inconsistent environments.
+
+**Fields:** `source_depset`, `packages`, `output`
+
+```yaml
+- name: relaxed_data_ci_depset_${PYTHON_SHORT}
+  operation: relax
+  source_depset: data_base_ci_depset_${PYTHON_SHORT}
+  packages:
+    - pyarrow
+    - numpy
+    - datasets
+  output: python/deplocks/ci/relaxed_data-ci_depset_py${PYTHON_VERSION}.lock
+```
+
+### Config file format
+
+Configs use the `.depsets.yaml` extension and live in `ci/raydepsets/configs/`.
+
+**Top-level keys:**
+- `build_arg_sets` (optional) — template variable sets for matrix expansion
+- `depsets` — list of dependency set definitions
+
+**Template variables** use `${VARIABLE_NAME}`. When a depset lists multiple `build_arg_sets`, it expands into one concrete depset per set.
+
+| Field | Type | Description |
+|---|---|---|
+| `name` | string | Unique identifier (supports `${VAR}` substitution) |
+| `operation` | string | `compile`, `subset`, `expand`, or `relax` |
+| `output` | string | Output lock file path relative to workspace root |
+| `build_arg_sets` | list | Which build arg sets to expand with |
+| `append_flags` | list | Additional flags passed to `uv pip compile` |
+| `override_flags` | list | Flags that replace matching defaults |
+| `pre_hooks` | list | Shell commands to run before execution |
+| `include_setuptools` | bool | Allow setuptools in output (default: `false`) |
+
+**YAML anchors** are supported for DRY config:
+```yaml
+.common_settings: &common_settings
+  append_flags:
+    - --python-version=${PYTHON_VERSION_STR}
+    - --unsafe-package ray
+  build_arg_sets: [cpu, cu128]
+
+depsets:
+  - name: my_depset
+    <<: *common_settings
+    operation: compile
+    requirements: [requirements.txt]
+    output: output.lock
+```
+
+### Default `uv pip compile` flags
+
+Applied automatically to every `compile` call:
+```
+--no-header
+--generate-hashes
+--index-strategy unsafe-best-match
+--no-strip-markers
+--emit-index-url
+--emit-find-links
+--quiet
+--unsafe-package setuptools  (unless include_setuptools: true)
+```
+
+### Pre-hooks
+
+Shell scripts that run before a depset executes. Modeled as nodes in the DAG.
+
+- `ci/raydepsets/pre_hooks/build-placeholder-wheel.sh` — builds a placeholder Ray wheel so `uv pip compile` can resolve Ray as a dependency
+- `ci/raydepsets/pre_hooks/remove-compiled-headers.sh ${PYTHON_VERSION}` — copies `requirements_compiled` to `/tmp/ray-deps/` and strips GPU index URLs (`--extra-index-url`, `--find-links`) so they don't leak into CPU lock files
+
+### Existing config files
+
+| Config | Purpose |
+|---|---|
+| `rayimg.depsets.yaml` | Core Ray Docker images (`ray_img_depset_*`, `ray_base_deps_*`, `ray_base_extra_*`, `ray_base_slim_*`, CPU/GPU/ML/LLM variants) |
+| `rayllm.depsets.yaml` | RayLLM dependencies |
+| `ci_data.depsets.yaml` | Ray Data CI tests (pyarrow latest/v9/nightly variants, mongo) |
+| `ci_serve.depsets.yaml` | Ray Serve CI tests |
+| `data_test.depsets.yaml` | Data test dependencies |
+| `docs.depsets.yaml` | Documentation build dependencies |
+| `llm_release_tests.depsets.yaml` | LLM release benchmarks |
+| `release_compiled_graph_gpu_cu130.depsets.yaml` | Compiled graph GPU tests |
+| `release_multimodal_inference_benchmarks_tests.depsets.yaml` | Multimodal benchmarks (audio, embedding, image, video) |
+
+### Docker image hierarchy
+
+The Ray Docker image layer structure (from `rayimg.depsets.yaml`):
+
+```
+ray_img_depset_* (compile: core Ray image deps)
+  ├── ray_base_slim_* (expand: minimal slim image)
+  ├── ray_base_extra_testdeps_* (expand: full test deps, CPU)
+  │     ├── ray_base_deps_* (subset: first Docker layer)
+  │     └── ray_base_extra_* (subset: second Docker layer)
+  ├── ray_base_extra_testdeps_gpu_* (expand: GPU test deps with CUDA)
+  ├── ray_base_extra_testdeps_llm_cuda_* (expand: LLM+CUDA test deps)
+  ├── ray_ml_base_extra_testdeps_cuda_* (expand: ML+CUDA test deps)
+  └── ray_base_deps_tpu_* (expand: TPU deps)
+```
+
+Cross-config dependencies are supported — e.g., `ci_data.depsets.yaml` references `ray_img_depset_*` from `rayimg.depsets.yaml`.
+
+---
+
+## Marker preservation (pip-compile, py313 / multi-Python locks)
+
+`pip-compile` (pip-tools 7.4.1, the version `ci/ci.sh` uses) **strips `python_version` markers** from output pins UNLESS the source declaration is **an exact-version pin with the marker attached**. This matters because `requirements_compiled_py3.13.txt` is consumed as a constraint at multiple `--python-version` targets via uv.
+
+**What works (markers survive):**
+```
+onnxruntime==1.18.0 ; ... and python_version <= '3.10'
+onnxruntime==1.24.4 ; ... and python_version > '3.10'
+```
+Both exact pins, each with a marker. pip-compile at py3.11 evaluates the first as false → dropped; second as true → kept. Output retains the marker. When uv consumes the lock as constraint at `--python-version=3.10`, the marker is false → constraint skipped → resolver picks an older version from the source `.in` / `.txt`.
+
+**What does NOT work (markers get stripped):**
+```
+scipy<1.16 ; python_version < '3.11'
+scipy ; python_version >= '3.11'
+```
+A range cap + an unconstrained entry. Because scipy is also pulled transitively by many other packages with no marker, the consolidated pin loses the marker. Output: bare `scipy==1.17.1`, which then forces py3.10 depset compiles to fail (no cp310 wheel).
+
+**Fix pattern — two exact pins:**
+```
+scipy==1.15.3 ; python_version < '3.11'
+scipy==1.17.1 ; python_version >= '3.11'
+```
+Even though only one branch wins at compile time, the winning exact pin survives the transitive merge because its `==A.B.C` is more specific than any transitive range.
+
+**Where to put the pins:**
+- Broad cross-cutting compat → `python/requirements.txt`
+- ML-specific compat → `python/requirements/ml/py313/ml-requirements.txt`
+- Test-stack compat → `python/requirements/py313/test-requirements.txt`
+- Don't pin in `python/requirements/ml/py313/dl-cpu-requirements.txt` for things unrelated to CPU torch.
+
+**Classes of cliff to watch for when bumping py313 lock:**
+1. Dropped cp310 wheels (most common; detectable via PyPI `Requires-Python` ≥ 3.11).
+2. Transitive upper bounds from py<3.11-only deps (e.g. `tensorflow-metadata==1.17.3` caps `protobuf<=6.32` on py<3.11; not auto-detectable from `Requires-Python`).
+3. Transitive extras that pull new deps in newer versions (e.g. `jsonschema==4.25+` adds `rfc3987-syntax` to its `format-nongpl` extra, which pulls `lark==1.3.1` and clashes with vllm's `lark==1.2.2`).
+4. CPU-compile transitive pulls that conflict with GPU depsets (e.g. xgboost's unpinned `nvidia-nccl-cu12` can resolve to a version that conflicts with cu128 torch's pinned nccl — fix by pinning `nvidia-nccl-cu12==<cu128-matching-version>` in `dl-cpu-requirements.txt`).
+
+---
+
+## Commands
+
+### Build all depsets from a config
+```bash
+bazelisk run //ci/raydepsets:raydepsets -- build ci/raydepsets/configs/rayimg.depsets.yaml
+```
+
+### Build a single named depset (and its dependencies)
+```bash
+bazelisk run //ci/raydepsets:raydepsets -- build ci/raydepsets/configs/rayimg.depsets.yaml --name ray_img_depset_313
+```
+
+### Build all configs at once
+```bash
+bazelisk run //ci/raydepsets:raydepsets -- build --all-configs
+```
+
+### Validate lock files are up-to-date (CI check mode)
+```bash
+bazelisk run //ci/raydepsets:raydepsets -- build ci/raydepsets/configs/rayimg.depsets.yaml --check
+```
+
+### Recompile everything (compiled requirements + all lock files)
+```bash
+ci/ci.sh compile_pip_dependencies && bazelisk run //ci/raydepsets:raydepsets -- build --all-configs
+```
+
+### Run raydepsets tests
+```bash
+bazel test //ci/raydepsets:test_cli
+bazel test //ci/raydepsets:test_workspace
+```
+
+---
+
+## Common workflows
+
+### Adding a new dependency to a Ray component
+
+1. Identify the correct source requirements file (e.g., `python/requirements/ml/py313/data-requirements.txt` for Ray Data on py313).
+2. Add the package with appropriate version bounds (`>=min,<max`). Use the dual-exact-pin-with-markers pattern if the version differs across Python versions.
+3. Recompile monorepo deps: `ci/ci.sh compile_pip_dependencies`.
+4. Rebuild affected lock files: `bazelisk run //ci/raydepsets:raydepsets -- build ci/raydepsets/configs/<relevant>.depsets.yaml`.
+5. Verify with `--check`.
+
+### Creating a new CI test environment
+
+1. Create a `.in` file listing the extra packages.
+2. Create or edit a `.depsets.yaml` config in `ci/raydepsets/configs/`.
+3. Choose the right base depset to expand from (usually `ray_img_depset_*` for CPU, or a GPU variant).
+4. Define the depset with `operation: expand`, referencing the base and your new requirements.
+5. Output to `python/deplocks/ci/<name>.lock` or appropriate path.
+6. Build and verify with `bazelisk run //ci/raydepsets:raydepsets -- build ci/raydepsets/configs/<your-config>.depsets.yaml`.
+
+### Debugging a dependency conflict
+
+1. Read the failing lock file and the error from `uv pip compile`.
+2. Check constraints — the constraints file pins versions; conflicts arise when a new requirement is incompatible.
+3. Decide whether the right fix is a source-file pin (preferred), a marker-gated dual pin, or — as a last resort — a `relax` on the base depset.
+4. Check cross-config dependencies — a depset in one config may depend on depsets from another config.
+5. Use `--name` to rebuild just the failing depset for faster iteration.
+
+### Upgrading a package across all lock files
+
+1. Update the version in the source requirements file.
+2. Recompile: `ci/ci.sh compile_pip_dependencies`.
+3. Rebuild: `bazelisk run //ci/raydepsets:raydepsets -- build --all-configs`.
+4. Review diffs in the generated lock files to verify the upgrade propagated.
+
+---
+
+## Patterns and gotchas
+
+- **CUDA variants:** GPU depsets typically use `--index https://download.pytorch.org/whl/<cuda_code>` to pull PyTorch from the correct CUDA index.
+- **Platform targeting:** Use `--python-platform=linux` or `--python-platform=x86_64-manylinux_2_31` for Linux-specific resolution.
+- **`--unsafe-package ray`:** Always include so `uv` doesn't try to resolve Ray from PyPI (we use a local build).
+- **Constraint files at `/tmp/ray-deps/`:** Created by `remove-compiled-headers.sh`; GPU-stripped versions of `requirements_compiled`.
+- **`include_setuptools: true`:** Only set for base-deps and TPU depsets that need setuptools at runtime.
+- **Cross-config references:** A depset in `ci_data.depsets.yaml` can reference `ray_img_depset_*` defined in `rayimg.depsets.yaml` because all configs are loaded under `--all-configs` (or pulled in transitively when one config's depset depends on a node from another).
+- **Lock file output paths:** Docker image deps go to `python/deplocks/`; release test deps go to `release/ray_release/byod/`.

.claude/skills/rebuild/SKILL.md

@@ -0,0 +1,82 @@
+---
+name: rebuild
+description: Rebuild Ray from source — determines the right build mode based on what changed
+---
+
+# Rebuild Ray
+
+Canonical build docs: doc/source/ray-contribute/development.md
+Use the user's configured Python from CLAUDE.local.md, or fall back to `which python`.
+Update this skill if any changes are detected in development.rst.
+
+## Determine what to rebuild
+
+1. Check what files changed: `git diff --name-only HEAD` (or ask the user)
+2. Pick the appropriate build mode:
+   - **Only .py files changed** (no .h, .cc, .pyx, .pxd) → Python-only rebuild (not required if installed with `pip install -e .` — editable mode auto-picks up Python changes)
+   - **.h, .cc, .pyx, .pxd files changed** → C++/Cython rebuild
+   - **Dashboard files changed** (python/ray/dashboard/client/) → Dashboard rebuild first
+   - **First time / clean build** → Full source build
+
+**Running Python tests that exercise C++ changes:** When a Python test depends on
+C++ or Cython code (raylet, GCS, core_worker, etc.), run the C++/Cython rebuild
+below before running the test. Editable Python installs do not rebuild the compiled
+extensions, so stale binaries will run otherwise.
+
+## Python-only rebuild
+
+For changes to Tune, RLlib, Autoscaler, and most Python files.
+Two approaches depending on how Ray was installed:
+
+### If installed with `pip install -e .` (editable/full source build)
+No rebuild needed — Python changes are picked up automatically.
+
+### If installed from nightly wheel + setup-dev.py
+1. Ensure a nightly wheel is installed (see doc/source/ray-contribute/development.md
+   for the correct wheel URL for the user's platform and Python version)
+2. Link local files: `python python/ray/setup-dev.py`
+3. Can skip specific dirs: `python python/ray/setup-dev.py -y --skip _private dashboard`
+
+**Warning:** With setup-dev.py, don't run `pip uninstall ray` or `pip install -U`.
+Instead: `rm -rf <site-packages>/ray`, reinstall wheel, re-run setup-dev.py.
+
+## C++/Cython rebuild (after initial full build)
+
+### Full package rebuild
+```bash
+bazel run //:gen_ray_pkg
+```
+
+### Build individual modules (faster)
+```bash
+bazel build //src/ray/raylet:raylet          # Raylet only
+bazel build //src/ray/gcs:gcs_server         # GCS server only
+bazel build //src/ray/core_worker:core_worker # Core worker only
+bazel build //:ray_pkg                       # All C++ and Cython
+```
+
+### Build variants
+- `bazel run -c fastbuild //:gen_ray_pkg` — fast build (less optimization)
+- `bazel run -c dbg //:gen_ray_pkg` — debug build with symbols (for gdb)
+- `bazel run -c opt //:gen_ray_pkg` — optimized build
+
+Make permanent in `~/.bazelrc`: `build --compilation_mode=fastbuild`
+
+## Full source build (first time)
+
+1. If dashboard changed: `cd python/ray/dashboard/client && npm ci && npm run build && cd -`
+2. Install deps: `cd python/ && pip install -r requirements.txt`
+3. Build: `pip install -e . --verbose`
+
+## Resource-constrained builds
+Add to `~/.bazelrc` if machine runs out of memory:
+```
+build --local_ram_resources=HOST_RAM*.5 --local_cpu_resources=4
+build --disk_cache=~/bazel-cache
+```
+
+## Worktree notes
+- Verify build paths: `bazel info execution_root`
+- If build fails, check .bazelversion matches installed Bazel
+- Each worktree may need its own `pip install -e .`
+- If in a worktree and bazel targets fail, ensure symlinks are correct

.editorconfig

@@ -0,0 +1,28 @@
+root = true
+
+[*]
+indent_style = space
+end_of_line = lf
+
+[*.{bzl,bazel}]
+indent_size = 4
+
+[*.{h,hpp,hxx,cpp,cxx,cc,c}]
+indent_size = 2
+max_line_length = 90
+
+[*.html]
+indent_size = 2
+
+[*.java]
+indent_size = 2
+
+[*.proto]
+indent_size = 2
+
+[*.{py,pyx,pxd,pxi}]
+indent_size = 4
+max_line_length = 79
+
+[*.sh]
+indent_size = 2

.fossa.yml

@@ -0,0 +1,19 @@
+version: 3
+
+paths:
+  only:
+    - ./bazel
+    - ./ci
+    - ./cpp
+    - ./docker
+    - ./java
+    - ./python
+    - ./rllib
+    - ./scripts
+    - ./src
+    - ./thirdparty
+    - ./BUILD.bazel
+    - ./LICENSE
+    - ./SECURITY.md
+    - ./WORKSPACE
+    - ./pyproject.toml

.gemini/config.yaml

@@ -0,0 +1,10 @@
+have_fun: false
+code_review:
+  disable: false
+  comment_severity_threshold: MEDIUM
+  max_review_comments: -1
+  pull_request_opened:
+    help: false
+    summary: false
+    code_review: true
+ignore_patterns: []

.git-blame-ignore-revs

@@ -0,0 +1,2 @@
+# Formatted Python code with Black
+7f1bacc7dc9caf6d0ec042e39499bbf1d9a7d065

.github/CODEOWNERS

@@ -0,0 +1,160 @@
+# See https://help.github.com/articles/about-codeowners/
+# for more info about CODEOWNERS file
+
+# It uses the same pattern rule for gitignore file,
+# see https://git-scm.com/docs/gitignore#_pattern_format.
+
+
+# ==== Documentation ====
+
+# Authors responsible for documentation infrastructure and layout.
+# ray-ci co-owns doc CI/build config; ray-docs-reviewers is a silent fallback
+# (notifications disabled) so docs leads can unblock docs-required reviews.
+/doc/ @ray-project/ray-docs @ray-project/ray-ci @ray-project/ray-docs-reviewers
+
+# ==== Ray core ====
+
+# All C++ code.
+/src/ @ray-project/ray-core
+
+# Python worker.
+/python/ray/ @ray-project/ray-core
+
+# Java worker.
+/java/ @kfstorm @raulchen @WangTaoTheTonic @SongGuyang @ray-project/ray-core
+
+# C++ worker
+/cpp/ @SongGuyang @raulchen @kfstorm @ray-project/ray-core
+
+/doc/source/cluster/ @ray-project/ray-core @ray-project/ray-docs
+/doc/source/ray-core/ @ray-project/ray-core @ray-project/ray-docs
+
+/doc/source/cluster/kubernetes/ @andrewsykim @ray-project/ray-core @ray-project/ray-docs
+
+# Public protobuf files.
+/src/ray/protobuf/public/ @edoakes @dayshah @MengjinYan
+
+# Azure autoscaler
+/python/ray/autoscaler/azure/ @ray-project/ray-core @marosset @jackfrancis @alimaazamat
+/python/ray/autoscaler/_private/_azure/ @ray-project/ray-core @marosset @jackfrancis @alimaazamat
+
+# ==== Libraries and frameworks ====
+
+# Dependencies
+/python/setup.py @richardliaw @edoakes @ray-project/ray-ci
+
+# Common directory shared by core and the libraries.
+# Stricter enforcement because this defines the public boundary supported by core.
+/python/ray/_common/ @edoakes @dayshah @MengjinYan
+
+# Ray data.
+/python/ray/data/ @ray-project/ray-data
+/doc/source/data/ @ray-project/ray-data @ray-project/ray-docs
+/python/ray/dashboard/modules/data/ @ray-project/ray-data
+/python/ray/dashboard/modules/metrics/dashboards/data_dashboard_panels.py @ray-project/ray-data
+
+# RLlib.
+/rllib/ @ray-project/ray-rllib
+/doc/source/rllib/ @ray-project/ray-rllib @ray-project/ray-docs
+
+# Ray Tune
+/python/ray/tune/ @ray-project/ray-tune
+/doc/source/tune/ @ray-project/ray-tune @ray-project/ray-docs
+
+# Ray Train
+/python/ray/train/ @ray-project/ray-train
+/doc/source/train/ @ray-project/ray-train @ray-project/ray-docs
+
+# Ray AIR
+/python/ray/air/ @ray-project/ray-train
+
+# Ray Serve
+/python/ray/serve/ @ray-project/ray-serve
+/java/serve/ @ray-project/ray-serve
+/src/ray/protobuf/serve.proto @ray-project/ray-serve
+/python/ray/dashboard/modules/serve/ @ray-project/ray-serve
+/doc/source/serve/ @ray-project/ray-serve @ray-project/ray-docs
+
+# LLM
+/python/ray/llm/ @ray-project/ray-llm
+/python/ray/data/llm.py @ray-project/ray-llm
+/python/ray/dashboard/modules/metrics/dashboards/serve_llm_dashboard_panels.py @ray-project/ray-llm
+/python/ray/dashboard/modules/metrics/dashboards/serve_llm_grafana_dashboard_base.json @ray-project/ray-llm
+/python/ray/serve/llm/ @ray-project/ray-llm
+/doc/source/serve/llm/ @ray-project/ray-llm @ray-project/ray-docs
+/doc/source/data/working-with-llms.rst @ray-project/ray-llm @ray-project/ray-docs
+/doc/source/data/doc_code/working-with-llms/ @ray-project/ray-llm @ray-project/ray-docs
+
+# LLM dependencies
+/python/requirements/llm/llm-requirements.txt @ray-project/ray-llm
+/python/deplocks/llm/ @ray-project/ray-llm
+
+# ML Docker Dependencies
+/python/requirements/ml/dl-cpu-requirements.txt @richardliaw @matthewdeng
+/python/requirements/ml/dl-gpu-requirements.txt @richardliaw @matthewdeng
+
+# Ray symbol export
+/src/ray/ray_version_script.lds @ray-project/ray-core
+/src/ray/ray_exported_symbols.lds @ray-project/ray-core
+
+# Ray usage stats
+/python/ray/_private/usage/ @edoakes @richardliaw
+/python/ray/dashboard/modules/usage_stats/ @edoakes @richardliaw
+/src/ray/protobuf/usage.proto @pcmoritz @thomasdesr
+
+
+# ==== Build and CI ====
+
+# Bazel.
+/BUILD.bazel @ray-project/ray-core @ray-project/ray-ci
+/WORKSPACE @ray-project/ray-core @ray-project/ray-ci
+/bazel/ @ray-project/ray-core @ray-project/ray-ci
+
+# CI scripts. More specific /ci/ rules below override this catch-all.
+/ci/ @ray-project/ray-core @ray-project/ray-ci
+
+# CI
+/ci/docker @ray-project/ray-ci
+/ci/ray_ci @ray-project/ray-ci
+/ci/ray_ci/serve_di_test_names.txt @ray-project/ray-serve
+/ci/ray_ci/serve_hap_test_names.txt @ray-project/ray-serve
+
+/.rayciversion @ray-project/ray-ci
+
+# Buildkite pipeline management
+.buildkite/hooks @ray-project/ray-ci
+
+# Buildkite pipeline definitions and the change-detection rules that decide
+# what CI runs for every PR. Editing these changes what runs for everyone.
+/.buildkite/*.rayci.yml @ray-project/ray-ci
+/.buildkite/test.rules.txt @ray-project/ray-ci
+/.buildkite/always.rules.txt @ray-project/ray-ci
+
+# Compiled dependency lockfile. Gates the build and test environment.
+/python/requirements_compiled.txt @ray-project/ray-ci
+
+# Read the Docs build configuration. ray-docs owns the docs build; ray-ci
+# co-owns, and ray-docs-reviewers is a silent fallback for backup approval.
+/.readthedocs.yaml @ray-project/ray-docs @ray-project/ray-ci @ray-project/ray-docs-reviewers
+
+/release/ray_release @ray-project/ray-ci
+/release/release_tests.yaml @ray-project/ray-ci
+
+# Allow people to add BYOD post-installation shell scripts
+# on their own.
+/release/ray_release/byod/*.sh
+/release/ray_release/byod/*.lock
+/release/ray_release/byod/requirements_*.in
+/release/ray_release/byod/requirements_*.txt
+
+/.github/ISSUE_TEMPLATE/ @ray-project/ray-ci
+
+/.github/workflows/ @ray-project/ray-ci
+
+/.gemini/ @edoakes @ray-project/ray-ci
+
+# TPU
+/python/ray/util/tpu.py @andrewsykim @edoakes @ryanaoleary
+/python/ray/tests/test_tpu.py @andrewsykim @edoakes @ryanaoleary
+/python/ray/tests/accelerators/test_tpu.py @andrewsykim @edoakes @ryanaoleary
+/python/ray/_private/accelerators/tpu.py @andrewsykim @edoakes @ryanaoleary

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -0,0 +1,62 @@
+name: Bug report
+title: "[<Ray component: Core|RLlib|etc...>] "
+description: Problems and issues with code of Ray
+labels: [bug, triage]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thank you for reporting the problem!
+        Please make sure what you are reporting is a bug with reproducible steps. To ask questions
+        or share ideas, please post on our [Discussion page](https://discuss.ray.io/) instead.
+
+  - type: textarea
+    attributes:
+      label: What happened + What you expected to happen
+      description: Describe 1. the bug 2. expected behavior 3. useful information (e.g., logs)
+      placeholder: >
+        Please provide the context in which the problem occurred and explain what happened. Further,
+        please also explain why you think the behaviour is erroneous. It is extremely helpful if you can
+        copy and paste the fragment of logs showing the exact error messages or wrong behaviour here.
+
+        **NOTE**: please copy and paste texts instead of taking screenshots of them for easy future search.
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: Versions / Dependencies
+      description: Please specify the versions of Ray, Python, OS, and other libraries that are used.
+      placeholder: >
+        Please specify the versions of dependencies.
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: Reproduction script
+      description: >
+        Please provide a reproducible script. Providing a narrow reproduction (minimal / no external dependencies) will
+        help us triage and address issues in the timely manner!
+      placeholder: >
+        Please provide a short code snippet (less than 50 lines if possible) that can be copy-pasted to
+        reproduce the issue. The snippet should have **no external library dependencies**
+        (i.e., use fake or mock data / environments).
+
+        **NOTE**: If the code snippet cannot be run by itself, the issue will be marked as "needs-repro-script"
+        until the repro instruction is updated.
+    validations:
+      required: true
+
+  - type: dropdown
+    attributes:
+      label: Issue Severity
+      description: |
+        How does this issue affect your experience as a Ray user?
+      multiple: false
+      options:
+          - "Low: It annoys or frustrates me."
+          - "Medium: It is a significant difficulty but I can work around it."
+          - "High: It blocks me from completing my task."
+    validations:
+        required: false

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,5 @@
+blank_issues_enabled: true
+contact_links:
+  - name: Ask a question or get support
+    url: https://discuss.ray.io/
+    about: Ask a question or request support for using Ray

.github/ISSUE_TEMPLATE/documentation-issue.yml

@@ -0,0 +1,26 @@
+name: Documentation
+title: "[<Ray component: Core|RLlib|etc...>] "
+description: Report an issue with the Ray documentation
+labels: [docs, triage]
+body:
+  - type: markdown
+    attributes:
+      value: Thank you for helping us improve the Ray documentation!
+
+  - type: textarea
+    attributes:
+      label: Description
+      description: |
+        Tell us about the change you'd like to see. For example, "I'd like to
+        see more examples of how to use `ray.remote`."
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: Link
+      description: |
+        If the problem is related to an existing section, please add a link to
+        the section. For example, https://docs.ray.io/en/master/ray-core/package-ref.html#ray.remote.
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/feature-request.yml

@@ -0,0 +1,25 @@
+name: Ray feature request
+description: Suggest an idea for Ray project
+title: "[<Ray component: Core|RLlib|etc...>] "
+labels: [enhancement, triage]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thank you for finding the time to propose a new feature!
+        We really appreciate the community efforts to improve Ray.
+
+  - type: textarea
+    attributes:
+      label: Description
+      description: A short description of your feature
+
+  - type: textarea
+    attributes:
+      label: Use case
+      description: >
+        Describe the use case of your feature request. It will help us understand and
+        prioritize the feature request.
+      placeholder: >
+        Rather than telling us how you might implement this feature, try to take a
+        step back and describe what you are trying to achieve.

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,15 @@
+> Thank you for contributing to Ray! 🚀
+> Please review the [Ray Contribution Guide](https://docs.ray.io/en/master/ray-contribute/getting-involved.html) before opening a pull request.
+
+> ⚠️ Remove these instructions before submitting your PR.
+
+> 💡 Tip: Mark as draft if you want early feedback, or ready for review when it's complete.
+
+## Description
+> Briefly describe what this PR accomplishes and why it's needed.
+
+## Related issues
+> Link related issues: "Fixes #1234", "Closes #1234", or "Related to #1234".
+
+## Additional information
+> Optional: Add implementation details, API changes, usage examples, screenshots, etc.

.github/dependabot.yml

@@ -0,0 +1,43 @@
+version: 2
+updates:
+  # ML Requirements.
+  - package-ecosystem: "pip"
+    # If we want to add more requirements here (Core, Serve, etc.), then we should
+    # make additional subdirectories for each one.
+    directory: "/python/requirements/ml"
+    schedule:
+      # Automatic upgrade checks Saturday at 12 AM.
+      # Dependabot updates can still be manually triggered via Github at any time.
+      interval: "weekly"
+      day: "saturday"
+      # 12 AM
+      time: "00:00"
+      # Use Pacific Standard Time.
+      timezone: "America/Los_Angeles"
+    commit-message:
+      prefix: "[air]"
+      include: "scope"
+    # Only 5 upgrade PRs open at a time.
+    open-pull-requests-limit: 5
+    reviewers:
+      - "ray-project/ray-tune"
+  # Data Requirements.
+  - package-ecosystem: "pip"
+    directory: "/python/requirements/data_processing"
+    schedule:
+      # Automatic upgrade checks Saturday at 12 AM.
+      # Dependabot updates can still be manually triggered via Github at any time.
+      interval: "weekly"
+      day: "saturday"
+      # 12 AM
+      time: "00:00"
+      # Use Pacific Standard Time.
+      timezone: "America/Los_Angeles"
+    commit-message:
+      prefix: "[data]"
+      include: "scope"
+    # Only 5 upgrade PRs open at a time.
+    open-pull-requests-limit: 5
+    reviewers:
+      - "scv119"
+      - "clarkzinzow"

.github/workflows/notify-slack-on-label.yml

@@ -0,0 +1,136 @@
+name: Notify Slack on Labeled Issue or PR
+
+on:
+  issues:
+    types: [labeled]
+  pull_request:
+    types: [labeled]
+
+jobs:
+  notify:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Notify Slack Channel Based on Label
+        uses: actions/github-script@v7
+        with:
+          script: |
+            // ── Label → Slack webhook secret name mapping ──────────────────────
+            // Add or remove entries here as you add/remove Ray library channels.
+            // The key is the GitHub label name; the value is the name of the
+            // GitHub Actions secret that holds that channel's Incoming Webhook URL.
+            const LABEL_TO_SECRET = {
+              "serve":        "SLACK_WEBHOOK_SERVE",
+              "train":        "SLACK_WEBHOOK_TRAIN",
+              "tune":         "SLACK_WEBHOOK_TUNE",
+              "rllib":        "SLACK_WEBHOOK_RLLIB",
+              "data":         "SLACK_WEBHOOK_DATA",
+              "air":          "SLACK_WEBHOOK_AIR",
+              "core":         "SLACK_WEBHOOK_CORE",
+              "workflow":     "SLACK_WEBHOOK_WORKFLOW",
+              "cluster":      "SLACK_WEBHOOK_CLUSTER",
+            };
+
+            // ── Resolve the webhook URLs from secrets ──────────────────────────
+            // We pass secrets in as env vars so the script can read them safely.
+            const SECRET_VALUES = {
+              "SLACK_WEBHOOK_SERVE":    process.env.SLACK_WEBHOOK_SERVE,
+              "SLACK_WEBHOOK_TRAIN":    process.env.SLACK_WEBHOOK_TRAIN,
+              "SLACK_WEBHOOK_TUNE":     process.env.SLACK_WEBHOOK_TUNE,
+              "SLACK_WEBHOOK_RLLIB":    process.env.SLACK_WEBHOOK_RLLIB,
+              "SLACK_WEBHOOK_DATA":     process.env.SLACK_WEBHOOK_DATA,
+              "SLACK_WEBHOOK_AIR":      process.env.SLACK_WEBHOOK_AIR,
+              "SLACK_WEBHOOK_CORE":     process.env.SLACK_WEBHOOK_CORE,
+              "SLACK_WEBHOOK_WORKFLOW": process.env.SLACK_WEBHOOK_WORKFLOW,
+              "SLACK_WEBHOOK_CLUSTER":  process.env.SLACK_WEBHOOK_CLUSTER,
+            };
+
+            // ── Determine event type and payload ──────────────────────────────
+            const isPR    = !!context.payload.pull_request;
+            const item    = isPR ? context.payload.pull_request : context.payload.issue;
+            const type    = isPR ? "Pull Request" : "Issue";
+            const action  = context.payload.action;           // "opened" | "labeled"
+            const labels  = (item.labels || []).map(l => l.name);
+
+            // On "labeled" events, only act on the label that was just added
+            // (avoids duplicate messages when multiple labels already exist).
+            const triggeredLabel = action === "labeled"
+              ? context.payload.label.name
+              : null;
+
+            const labelsToProcess = triggeredLabel ? [triggeredLabel] : labels;
+
+            // ── Send a message for each matching label ─────────────────────────
+            for (const label of labelsToProcess) {
+              const secretName = LABEL_TO_SECRET[label];
+              if (!secretName) continue;                      // label not mapped
+
+              const webhookUrl = SECRET_VALUES[secretName];
+              if (!webhookUrl) {
+                core.warning(`Secret ${secretName} is not set — skipping #${label}`);
+                continue;
+              }
+
+              // Build a rich Slack Block Kit message
+              const allLabelNames = labels.map(l => `\`${l}\``).join(" ");
+              const body = {
+                blocks: [
+                  {
+                    type: "section",
+                    text: {
+                      type: "mrkdwn",
+                      text: `*New ${type} in <https://github.com/${context.repo.owner}/${context.repo.repo}|${context.repo.owner}/${context.repo.repo}>*`
+                    }
+                  },
+                  {
+                    type: "section",
+                    fields: [
+                      { type: "mrkdwn", text: `*Title*\n<${item.html_url}|${item.title}>` },
+                      { type: "mrkdwn", text: `*Author*\n<${item.user.html_url}|${item.user.login}>` },
+                      { type: "mrkdwn", text: `*Labels*\n${allLabelNames || "_none_"}` },
+                      { type: "mrkdwn", text: `*#*\n${item.number}` },
+                    ]
+                  },
+                  ...(item.body ? [{
+                    type: "section",
+                    text: {
+                      type: "mrkdwn",
+                      // Truncate long bodies so the message stays readable
+                      text: `*Description*\n${item.body.slice(0, 300)}${item.body.length > 300 ? "…" : ""}`
+                    }
+                  }] : []),
+                  {
+                    type: "actions",
+                    elements: [
+                      {
+                        type: "button",
+                        text: { type: "plain_text", text: `View ${type}` },
+                        url: item.html_url,
+                        style: "primary"
+                      }
+                    ]
+                  }
+                ]
+              };
+
+              const response = await fetch(webhookUrl, {
+                method: "POST",
+                headers: { "Content-Type": "application/json" },
+                body: JSON.stringify(body)
+              });
+
+              if (!response.ok) {
+                core.error(`Failed to post to Slack for label "${label}": ${response.status} ${response.statusText}`);
+              } else {
+                core.info(`Posted to Slack channel for label "${label}"`);
+              }
+            }
+        env:
+          SLACK_WEBHOOK_SERVE:    ${{ secrets.SLACK_WEBHOOK_SERVE }}
+          SLACK_WEBHOOK_TRAIN:    ${{ secrets.SLACK_WEBHOOK_TRAIN }}
+          SLACK_WEBHOOK_TUNE:     ${{ secrets.SLACK_WEBHOOK_TUNE }}
+          SLACK_WEBHOOK_RLLIB:    ${{ secrets.SLACK_WEBHOOK_RLLIB }}
+          SLACK_WEBHOOK_DATA:     ${{ secrets.SLACK_WEBHOOK_DATA }}
+          SLACK_WEBHOOK_AIR:      ${{ secrets.SLACK_WEBHOOK_AIR }}
+          SLACK_WEBHOOK_CORE:     ${{ secrets.SLACK_WEBHOOK_CORE }}
+          SLACK_WEBHOOK_WORKFLOW: ${{ secrets.SLACK_WEBHOOK_WORKFLOW }}
+          SLACK_WEBHOOK_CLUSTER:  ${{ secrets.SLACK_WEBHOOK_CLUSTER }}

.github/workflows/on_auto_merge.yaml

@@ -0,0 +1,19 @@
+name: Auto merge enabled
+on:
+  pull_request_target:
+    types:
+      - auto_merge_enabled
+jobs:
+  add-go-label:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Add go label
+        uses: actions/github-script@v5
+        with:
+          script: |
+            github.rest.issues.addLabels({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: context.issue.number,
+              labels: ['go']
+            })

.github/workflows/on_pull_request_synchronized.yml

@@ -0,0 +1,47 @@
+name: Pull request synchronized
+on:
+  pull_request_target:
+    types:
+      - synchronize
+    branches:
+      - "master"
+      - "releases/**"
+jobs:
+  disable-automerge:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/github-script@v7
+        with:
+          script: |
+            const prQuery = `query PullRequest($owner: String!, $repo: String!, $pullRequestNumber: Int!) {
+              repository(owner: $owner, name: $repo) {
+                pullRequest(number: $pullRequestNumber) {
+                  id
+                  autoMergeRequest {
+                    enabledAt
+                  }
+                }
+              }
+            }`;
+            const prVariables = {
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              pullRequestNumber: context.issue.number
+            }
+            const prResult = await github.graphql(prQuery, prVariables)
+            if (!prResult.repository.pullRequest.autoMergeRequest) {
+              console.log('Auto merge is not enabled')
+              return
+            }
+            const automergeQuery = `mutation DisablePullRequestAutoMerge($pullRequestId: ID!) {
+              disablePullRequestAutoMerge(input: {pullRequestId: $pullRequestId}) {
+                pullRequest {
+                  id
+                }
+              }
+            }`;
+            const automergeVariables = {
+              pullRequestId: prResult.repository.pullRequest.id
+            }
+            const result = await github.graphql(automergeQuery, automergeVariables)
+            console.log(result)

.github/workflows/stale_pull_request.yaml

@@ -0,0 +1,75 @@
+name: Mark and Close Stale Pull Requests
+
+on:
+  schedule:
+    # Runs twice a day at 15 minutes past midnight and noon UTC
+    - cron: '15 */12 * * *'
+
+jobs:
+  stale:
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write # Required to add labels, comment, close PRs.
+
+    steps:
+      - name: Mark and Close Stale Pull Requests
+        uses: actions/stale@v9
+        with:
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+
+          # --- Ignore Issues ---
+          # Set to -1 so we never mark issues as stale or closed.
+          days-before-issue-stale: -1
+          days-before-issue-close: -1
+
+          # --- Pull Request Specific Settings ---
+          # Number of days of inactivity before a Pull Request becomes stale (currently 2 weeks)
+          days-before-pr-stale: 14
+
+          # Number of days of inactivity after being marked stale before a Pull Request is closed (2 more weeks)
+          days-before-pr-close: 14
+
+          # Label to use when marking a PR as stale
+          stale-pr-label: 'stale'
+
+          # Comment to post when marking a PR as stale
+          stale-pr-message: |
+            This pull request has been automatically marked as stale because it has not had
+            any activity for 14 days. It will be closed in another 14 days if no further activity occurs.
+            Thank you for your contributions.
+
+            You can always ask for help on our [discussion forum](https://discuss.ray.io/) or [Ray's public slack channel](https://github.com/ray-project/ray#getting-involved).
+
+            If you'd like to keep this open, just leave any comment, and the stale label will be removed.
+
+          # Comment to post when closing a stale PR
+          close-pr-message: |
+            This pull request has been automatically closed because there has been no more activity in the 14 days
+            since being marked stale.
+
+            Please feel free to reopen or open a new pull request if you'd still like this to be addressed.
+
+            Again, you can always ask for help on our [discussion forum](https://discuss.ray.io) or [Ray's public slack channel](https://github.com/ray-project/ray#getting-involved).
+
+            Thanks again for your contribution!
+
+          # Pull Requests with these labels will never be considered stale
+          exempt-pr-labels: >
+            weekly-release-blocker,
+            release-blocker,
+            unstale
+
+          # Set to true to ignore PRs in a milestone (defaults to false)
+          exempt-all-pr-milestones: true
+
+          # --- Shared Settings & Other Options ---
+          # Limit the number of actions per run.
+          operations-per-run: 500
+
+          # Remove stale label from PRs on update (default is true)
+          remove-pr-stale-when-updated: true
+
+          # Add unstale label. Whenever a PR is marked as 'unstale' it will not be marked stale again.
+          labels-to-add-when-unstale: unstale
+
+          ascending: true

.gitignore

@@ -0,0 +1,256 @@
+# The build output should clearly not be checked in
+*test-output.xml
+/bazel-*
+/python/ray/core
+/python/ray/thirdparty_files/
+/python/ray/_private/runtime_env/agent/thirdparty_files/
+/python/ray/pyarrow_files/
+/python/ray/jars/
+/python/ray/cpp/
+/python/build
+/python/dist
+/python/python-driver-*
+/python/ray/serve/generated
+/thirdparty/pkg/
+/build/java
+.jar
+/dashboard/client/build
+/.whl
+
+# KubeRay config lives in a separate repository
+python/ray/autoscaler/kuberay/config
+
+# Files generated by flatc should be ignored
+/src/ray/gcs/format/*_generated.h
+/src/ray/object_manager/format/*_generated.h
+/src/ray/raylet/format/*_generated.h
+/java/runtime/src/main/java/io/ray/runtime/generated/*
+/java/serve/src/main/java/io/ray/serve/generated/*
+
+# Files genrated by c++ worker should be ignored.
+/cpp/example/thirdparty/
+/cpp/example/bazel-*
+/python/ray/cpp
+
+# Redis temporary files
+*dump.rdb
+
+# Python byte code files
+*.pyc
+__pycache__/
+python/.eggs
+.eggs
+# Backup files
+*.bak
+
+# Emacs temporary files
+*~
+*#
+
+# Compiled Object files
+*.slo
+*.lo
+*.o
+*.xo
+*.obj
+
+# Precompiled Headers
+*.gch
+*.pch
+
+# Compiled Dynamic libraries
+*.so
+*.dylib
+*.dll
+python/ray/_raylet.pyd
+
+# Incremental linking files
+*.ilk
+
+# Library export files
+*.exp
+
+# Debug symbols
+*.pdb
+
+# Compiled Static libraries
+*.lai
+*.la
+*.a
+*.lib
+
+# Executables
+*.exe
+*.out
+*.app
+
+# Visual Studio files
+/packages
+*.suo
+*.user
+*.VC.db
+*.VC.opendb
+
+# Protobuf-generated files
+*_pb2.py
+*.pb.h
+*.pb.cc
+
+# Ray cluster configuration
+scripts/nodes.txt
+
+# OS X folder attributes
+.DS_Store
+
+# Debug files
+*.dSYM/
+*.su
+
+# Python setup files
+*.egg-info
+
+# Compressed files
+*.gz
+
+# Datasets from examples
+**/MNIST_data/
+**/cifar-10-batches-bin/
+
+# Generated documentation files
+/doc/_build
+/doc/source/_static/thumbs
+/doc/source/tune/generated_guides/
+/doc/source/**/doc/
+
+# User-specific stuff:
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/dictionaries
+.llvm-local.bazelrc
+.user.bazelrc
+.aider*
+
+# Sensitive or high-churn files:
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.xml
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+
+# Gradle:
+.idea/**/gradle.xml
+.idea/**/libraries
+.idea
+
+# Website
+/site/Gemfile.lock
+/site/.sass-cache
+/site/_site
+
+# Pytest Cache
+**/.pytest_cache
+**/.cache
+.benchmarks
+python-driver-*
+
+# Ray Train unit test artifacts
+lightning_logs/
+hf-internal-testing/
+
+# Vscode
+.vscode/
+
+*.iml
+
+# Java
+java/**/target
+java/**/lib
+java/**/.settings
+java/**/.classpath
+java/**/.project
+java/runtime/native_dependencies/
+java/testng_custom.xml
+test-output
+
+dependency-reduced-pom.xml
+
+# Cpp
+cpp/example/thirdparty/
+
+.clwb
+
+# pom.xml files generated from pom_template.xml
+java/**/pom.xml
+
+# python virtual env
+venv
+.venv
+.conda
+
+# pyenv version file
+.python-version
+
+# Vim
+.*.swp
+*.swp
+.*.swo
+*.swo
+tags
+tags.lock
+tags.temp
+*.vim
+
+# Emacs
+.#*
+
+# tools
+tools/prometheus*
+
+# ray project files
+project-id
+.mypy_cache/
+
+# release test related
+.anyscale.yaml
+test_state.json
+
+# workflow storage
+workflow_data/
+
+# vscode java extention generated
+.factorypath
+
+# Jupyter notebook autosave checkpoints
+**/.ipynb_checkpoints/
+
+# Jupyter notebook temporary documents used by LSP
+.virtual_documents/
+
+### Added by Hedron's Bazel Compile Commands Extractor: https://github.com/hedronvision/bazel-compile-commands-extractor
+# The external link: Differs on Windows vs macOS/Linux, so we can't check it in. The pattern needs to not have a trailing / because it's a symlink on macOS/Linux.
+/external
+# Compiled output -> don't check in
+/compile_commands.json
+# Directory where clangd puts its indexing work
+/.cache/
+
+# Auto-generated tag mapping
+tag-mapping.json
+
+# Temporary files generated by import sorting linter.
+*.isorted
+
+# Custom BYOD build rayci yaml file
+.buildkite/release/custom_byod_build.rayci.yml
+
+# Claude Code — track shared config, ignore personal/local files
+/.claude/settings.local.json
+/CLAUDE.md
+/CLAUDE-*.md
+CLAUDE.local.md
+
+# Worktrees
+.worktrees/
+.claude/worktrees/

.pre-commit-config.yaml

@@ -0,0 +1,246 @@
+exclude: |
+  (?x)^(
+    python/ray/core/generated/|
+    python/ray/serve/generated/|
+    python/ray/cloudpickle/|
+    python/ray/dashboard/client/public/|
+    python/ray/tests/test_cli_patterns|
+    python/ray/_private/runtime_env/_clonevirtualenv.py|
+    python/ray/data/examples/data/|
+    release/release_logs/|
+    rllib/offline/tests/data|
+    thirdparty/patches/|
+    python/requirements/llm/patches/|
+    src/ray/thirdparty/|
+    doc/external/|
+    doc/source/|
+    doc/.claude/skills/sphinx-fix/tests/
+  )
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.4.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-added-large-files
+      - id: check-ast
+        exclude: |
+          (?x)(
+            python/ray/serve/tests/test_config_files/syntax_error\.py
+          )$
+      - id: check-json
+        exclude: |
+          (?x)^(
+            # Intentionally bad json schema
+            python/ray/tests/unit/test_runtime_env_validation_bad_schema.json
+          )
+      - id: check-toml
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.8.4
+    hooks:
+      - id: ruff
+        args: [ --fix, --exit-non-zero-on-fix ]
+      - id: ruff
+        args: [ --select, "I", --fix, --exit-non-zero-on-fix ]
+
+  - repo: https://github.com/jsh9/pydoclint
+    rev: "0.8.3"
+    hooks:
+      - id: pydoclint
+        args: [
+          --style=google,
+          --baseline=ci/lint/pydoclint-baseline.txt,
+          --exclude=thirdparty|^python/ray/serve/tests/test_config_files/syntax_error\.py$|^python/ray/_private/parameter\.py$,
+          # --generate-baseline=True, # Not generally needed, but documenting since this is how we generate the initial baseline
+          --auto-regenerate-baseline=True,
+          # Current settings (not because we think they're right, but because we
+          # don't want a baseline the size of the codebase)
+          --arg-type-hints-in-docstring=False,
+          --skip-checking-raises=True,
+          --check-return-types=False,
+          --allow-init-docstring=True,
+          --check-class-attributes=False,
+          --check-style-mismatch=True,
+        ]
+        types: [python]
+        files: '^python/ray/'
+
+  - repo: https://github.com/cpplint/cpplint
+    rev: 2.0.0
+    hooks:
+      - id: cpplint
+        args: ["--filter=-whitespace/braces,-whitespace/line_length,-build/c++11,-build/c++14,-build/c++17,-readability/braces,-whitespace/indent_namespace,-runtime/int,-runtime/references,-build/include_order"]
+        files: ^src/ray/(gcs/actor|common/cgroup2|common/scheduling|common/ray_syncer|common/test|util|raylet_client|internal|scheduling|pubsub|object_manager|rpc(?:/.*)?|raylet|core_worker|ipc)/.*\.(h|cc)$
+        exclude: |
+          (?x)^(
+            src/ray/raylet/scheduling/.*\.(h|cc)$ |
+            src/ray/core_worker/lib/java/.*\.h$
+          )
+
+  - repo: https://github.com/keith/pre-commit-buildifier
+    rev: 8.0.1
+    hooks:
+      - id: buildifier
+        files: ^(src|cpp|python|rllib|ci|release|java)(/[^/]+)*/BUILD(\.bazel)?$|^BUILD.bazel$
+      - id: buildifier-lint
+        files: ^(src|cpp|python|rllib|ci|release|java)(/[^/]+)*/BUILD(\.bazel)?$|^BUILD.bazel$
+
+  - repo: https://github.com/psf/black
+    rev: 22.10.0
+    hooks:
+      - id: black
+        exclude: |
+          (?x)^(
+            python/ray/cloudpickle/|
+            python/build/|
+            python/ray/core/src/ray/gcs/|
+            python/ray/thirdparty_files/|
+            python/ray/_private/thirdparty/|
+            python/ray/serve/tests/test_config_files/syntax_error\.py|
+            python/ray/serve/_private/benchmarks/streaming/_grpc/test_server_pb2_grpc\.py|
+            doc/external/
+          )
+        types_or: [python]
+
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: v3.0.3
+    hooks:
+      - id: prettier
+        files: 'doc/'
+        types_or: [javascript, ts, tsx, html, css]
+
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.7.0
+    hooks:
+      - id: mypy
+        args: ['--follow-imports=skip', '--ignore-missing-imports']
+        files: |
+          (?x)^(
+            python/ray/autoscaler/node_provider.py|
+            python/ray/autoscaler/sdk/__init__.py|
+            python/ray/autoscaler/sdk/sdk.py|
+            python/ray/autoscaler/_private/commands.py|
+            python/ray/autoscaler/_private/autoscaler.py|
+            python/ray/_private/gcs_utils.py|
+            python/ray/serve/handle.py|
+            python/ray/serve/tests/typing_files/check_handle_typing.py
+          )
+        additional_dependencies:
+          [
+            types-PyYAML==6.0.12.2,
+          ]
+
+  - repo: https://github.com/pre-commit/pygrep-hooks
+    rev: v1.10.0
+    hooks:
+      - id: rst-directive-colons
+      - id: rst-inline-touching-normal
+      - id: python-no-log-warn
+      - id: python-check-mock-methods
+
+  - repo: https://github.com/shellcheck-py/shellcheck-py
+    rev: v0.9.0.1
+    hooks:
+      - id: shellcheck
+        args: ['--exclude=1090,1091,2207']
+          # 1090: Can't follow non-constant source. Use a directive to specify location.
+          # 1091: Not following {file} due to some error
+          # 2207: Prefer mapfile or read -a to split command output (or quote to avoid splitting). -- these aren't compatible with macOS's old Bash
+
+  - repo: https://github.com/pre-commit/mirrors-clang-format
+    # `rev` specifies a tag on the above repo that mirrors the corresponding clang-format version.
+    rev: v12.0.1
+    hooks:
+      - id: clang-format
+
+  - repo: https://github.com/macisamuele/language-formatters-pre-commit-hooks
+    rev: v2.11.0
+    hooks:
+      - id: pretty-format-java
+        args: [--autofix, --google-java-formatter-version=1.7]
+        exclude: |
+          (?x)^(
+            java/api/src/main/java/io/ray/api/ActorCall.java|
+            java/api/src/main/java/io/ray/api/CppActorCall.java|
+            java/api/src/main/java/io/ray/api/PyActorCall.java|
+            java/api/src/main/java/io/ray/api/RayCall.java
+          )
+
+  - repo: local
+    hooks:
+      - id: docstyle
+        name: Check for Ray docstyle violations
+        entry: ci/lint/check-docstyle.sh
+        language: system
+        types: [python]
+
+  - repo: https://github.com/semgrep/pre-commit
+    rev: v1.32.0
+    hooks:
+      - id: semgrep
+        args: [--config=semgrep.yml, --error]
+
+  - repo: https://github.com/errata-ai/vale
+    rev: v3.4.1
+    hooks:
+      - id: vale
+        files: ^doc/source/data/.*\.(md|rst)$
+
+  - repo: https://github.com/MarcoGorelli/cython-lint
+    rev: v0.18.1
+    hooks:
+      - id: cython-lint
+        args: [--no-pycodestyle]
+
+  - repo: local
+    hooks:
+      - id: check-import-order
+        name: Check for Ray import order violations
+        entry: python ci/lint/check_import_order.py
+        language: python
+        types: [python]
+        pass_filenames: false
+        args: [".", "-s", "ci", "-s", "python/ray/thirdparty_files", "-s", "python/build", "-s", "lib"]
+
+  - repo: local
+    hooks:
+      - id: check-cpp-files-inclusion
+        name: Check ray core C++ files inclusion violations
+        entry: ci/lint/check_cpp_files_inclusion.py
+        language: python
+        files: '^src/ray/'
+        types: [c++]
+
+  - repo: local
+    hooks:
+    - id: check-train-circular-imports
+      name: Check Ray Train circular imports
+      entry: python python/ray/train/lint/check_circular_imports.py
+      language: system
+      types: [python]
+      files: '^python/ray/train/.*\.py$'
+      pass_filenames: false
+      args: ["--patch_dir", "ray/train/v2"]
+
+  - repo: https://github.com/pre-commit/mirrors-eslint
+    rev: v8.26.0
+    hooks:
+      - id: eslint
+        files: ^python/ray/dashboard/client/src/.*\.(tsx|ts)$
+        types: [file]
+        args:
+          - --max-warnings=0
+        additional_dependencies:
+          - eslint@8.26.0
+          - eslint-plugin-react@7.31.10
+          - eslint-plugin-import@2.26.0
+          - eslint-config-react-app@7.0.1
+          - eslint-plugin-prefer-arrow@1.2.3
+          - '@typescript-eslint/parser@5.41.0'
+          - '@typescript-eslint/eslint-plugin@5.41.0'
+          # Pin typescript: eslint-config-react-app declares `typescript: "*"`,
+          # which otherwise floats to a TS major incompatible with
+          # @typescript-eslint 5.41 and breaks plugin load in CI. Matches the
+          # dashboard client's own typescript devDependency.
+          - typescript@4.8.4

.prettierrc.toml

@@ -0,0 +1,3 @@
+singleQuote = true
+bracketSpacing = false
+htmlWhitespaceSensitivity = 'ignore'

.rayciversion

@@ -0,0 +1 @@
+0.46.0

.readthedocs.yaml

@@ -0,0 +1,84 @@
+# .readthedocs.yaml
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the version of Python and other tools you might need
+build:
+  os: ubuntu-24.04
+  tools:
+    python: "3.11"
+  jobs:
+    # On PR builds, skip the Sphinx build when the PR doesn't touch any
+    # files that affect documentation output. Reduces queue pressure on
+    # the shared RTD build slots when several PRs are open at once.
+    # Tag/branch builds (master, stable, etc.) always run.
+    # The guard matches doc/ but excludes doc/.claude/ (Claude Code skills
+    # and agent files), which never participate in the Sphinx build, so a
+    # PR that changes only those paths skips the build instead of running one.
+    # Code sources (python/ray/, rllib/) are intentionally not matched, so a
+    # code-only PR skips this PR preview. The RTD PR check is not a required
+    # merge gate, and the post-merge master build and the Buildkite doc_build
+    # still render docstring-driven API-reference changes. This trades a
+    # non-gating premerge preview for less pressure on the shared RTD slots.
+    # See https://docs.readthedocs.com/platform/stable/guides/build/skip-build.html
+    #
+    # Some constructs are avoided deliberately because RTD's job runner
+    # silently drops scripts that contain them: use echo (not printf
+    # with a backslash-escape format string), avoid backslash escapes
+    # in general, and keep shell comments out of this block so that
+    # backticks/$() inside comments don't confuse the preprocessor.
+    # The runner also strips the surrounding single quotes from arguments,
+    # so use git's :! exclude shorthand rather than :(exclude): unquoted
+    # parentheses reach /bin/sh (dash) and abort the script with a syntax error.
+    post_checkout:
+      - |
+        if [ "${READTHEDOCS_VERSION_TYPE:-}" != "external" ]; then
+          echo "Not a PR build (version type: '${READTHEDOCS_VERSION_TYPE:-unset}'); building docs."
+          exit 0
+        fi
+        git fetch --depth=500 origin master 2>/dev/null || true
+        if ! git merge-base origin/master HEAD >/dev/null 2>&1; then
+          echo "Could not determine merge-base with origin/master; building docs to be safe."
+          exit 0
+        fi
+        if git diff --quiet origin/master...HEAD -- doc/ ':!doc/.claude/' .readthedocs.yaml; then
+          echo "No doc-affecting files changed in this PR; skipping Sphinx build."
+          echo "Files changed in PR:"
+          git diff --name-only origin/master...HEAD
+          exit 183
+        fi
+        echo "Doc-affecting files changed; building docs. Changed doc-relevant paths:"
+        git diff --name-only origin/master...HEAD -- doc/ ':!doc/.claude/' .readthedocs.yaml
+    # Override the html build step so every build runs a full clean Sphinx
+    # build via the doc/Makefile html target, for PR (external) previews and
+    # branch/tag builds alike.
+    #
+    # The incremental-from-master-cache path added in #64277 is disabled for
+    # now. On every PR preview Sphinx discards the restored cache because a
+    # config value differs between the environment that produced the cache and
+    # the RTD build environment, so it rebuilds all documents anyway while
+    # still paying the cache download and extract cost, and it risks a second
+    # clean rebuild when the incremental leg trips a warning. A clean build is
+    # faster and lower-variance in practice today. Re-enable the incremental
+    # path only once cache reuse is confirmed (Sphinx logs "N changed" rather
+    # than "NNNN added") and stale-artifact pruning lands for PRs that rename
+    # or delete sources. The rtd and rtd-fallback Makefile targets and
+    # doc/load_doc_cache.py stay in the tree for that re-enable.
+    build:
+      html:
+        - |
+          make -C doc html HTMLDIR="$READTHEDOCS_OUTPUT/html"
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+  configuration: doc/source/conf.py
+  fail_on_warning: true
+
+# We recommend specifying your dependencies to enable reproducible builds:
+# https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
+python:
+  install:
+    - requirements: doc/requirements-doc.lock.txt

.vale.ini

@@ -0,0 +1,24 @@
+StylesPath = .vale/styles
+
+Vocab = General, Core, Data, RLlib, Train
+
+MinAlertLevel = suggestion
+
+Packages = Google
+
+[*.rst]
+# HACK(@bveeramani): I have no clue why we need to include `(:class:`.*`)` in addition
+# to `(:.*:`.*`)`, but we get false positives if we don't. `TokenIgnores` is weird.
+TokenIgnores = (:class:`.*`)|(:.*:`.*`)|(`.*`)
+
+[*.{md,rst}]
+BasedOnStyles = Vale, Google
+# We're disabling "Colons" because we disagree with Google's suggestion to lowercase the
+# first word after a colon.
+Google.Colons = No
+# TODO(@bveeramani): We're temporarily disabling "Heading". In the future, we'll update
+# all headings and enable this rule.
+Google.Headings = No
+
+# ignore the anchors of headers.
+BlockIgnores = (?m)(^\([\w-]+\)=$)

.vale/styles/Google/AMPM.yml

@@ -0,0 +1,9 @@
+extends: existence
+message: "Use 'AM' or 'PM' (preceded by a space)."
+link: 'https://developers.google.com/style/word-list'
+level: error
+nonword: true
+tokens:
+  - '\d{1,2}[AP]M'
+  - '\d{1,2} ?[ap]m'
+  - '\d{1,2} ?[aApP]\.[mM]\.'

.vale/styles/Google/Acronyms.yml

@@ -0,0 +1,79 @@
+extends: conditional
+message: "Spell out '%s', if it's unfamiliar to the audience."
+link: 'https://developers.google.com/style/abbreviations'
+level: error
+ignorecase: false
+# Ensures that the existence of 'first' implies the existence of 'second'.
+first: '\b([A-Z]{3,5})\b'
+second: '(?:\b[A-Z][a-z]+ )+\(([A-Z]{3,5})\)'
+# ... with the exception of these:
+exceptions:
+  - API
+  - ASP
+  - AWS
+  - CLI
+  - CPU
+  - CRD
+  - CSS
+  - CSV
+  - CUDA
+  - DEBUG
+  - DOM
+  - DPI
+  - DRF
+  - ETL
+  - FAQ
+  - GCC
+  - GCE
+  - GCP
+  - GCS
+  - GDB
+  - GET
+  - GPU
+  - GTK
+  - GUI
+  - HTML
+  - HTTP
+  - HTTPS
+  - IDE
+  - JAR
+  - JSON
+  - JSONL
+  - JSX
+  - KAI
+  - LESS
+  - LLDB
+  - MPS
+  - NET
+  - NFS
+  - NIXL
+  - NOTE
+  - NVDA
+  - OSS
+  - PATH
+  - PDF
+  - PHP
+  - PNG
+  - POST
+  - RAM
+  - RAG
+  - REPL
+  - RSA
+  - SCM
+  - SCSS
+  - SDK
+  - SQL
+  - SSH
+  - SSL
+  - SVG
+  - TBD
+  - TCP
+  - TODO
+  - URI
+  - URL
+  - USB
+  - UTF
+  - XML
+  - XSS
+  - YAML
+  - ZIP

.vale/styles/Google/Colons.yml

@@ -0,0 +1,8 @@
+extends: existence
+message: "'%s' should be in lowercase."
+link: 'https://developers.google.com/style/colons'
+nonword: true
+level: suggestion
+scope: sentence
+tokens:
+  - ':\s[A-Z]'