mirrors/ggml-org--llama.cpp
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity

chore: import upstream snapshot with attribution
Copilot Setup Steps / copilot-setup-steps (push) Failing after 2s
Details
Python check requirements.txt / check-requirements (push) Has been cancelled
Details
Python Type-Check / python type-check (push) Has been cancelled
Details
Update Operations Documentation / update-ops-docs (push) Has been cancelled
Details
Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Has been cancelled
Details

Browse Source
This commit is contained in:
wehub-resource-sync
2026-07-13 11:57:56 +08:00
commit 09a3d3ab17
3146 changed files with 1305073 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.clang-format
+171
View File
@@ -0,0 +1,171 @@
---
Language: Cpp
AlignAfterOpenBracket: Align
AlignArrayOfStructures: Left
AlignConsecutiveAssignments: AcrossComments
AlignConsecutiveBitFields: AcrossComments
AlignConsecutiveDeclarations: AcrossComments
AlignConsecutiveMacros: AcrossComments
# AlignConsecutiveShortCaseStatements: AcrossComments
AlignEscapedNewlines: Left # LeftWithLastLine
AlignOperands: Align
AlignTrailingComments:
Kind: Always
OverEmptyLines: 1
AllowAllArgumentsOnNextLine: true
AllowAllParametersOfDeclarationOnNextLine: false
# AllowBreakBeforeNoexceptSpecifier: OnlyWithParen
AllowShortBlocksOnASingleLine: Never
AllowShortCaseLabelsOnASingleLine: false
AllowShortFunctionsOnASingleLine: Inline
AllowShortIfStatementsOnASingleLine: Never
AllowShortLambdasOnASingleLine: Inline
AllowShortLoopsOnASingleLine: false
AlwaysBreakBeforeMultilineStrings: true
# Treat CUDA keywords/attributes as "attribute macros" and avoid breaking lines inside them
AttributeMacros:
- __host__
- __device__
- __global__
- __forceinline__
- __launch_bounds__
BinPackArguments: true
BinPackParameters: false # OnePerLine
BitFieldColonSpacing: Both
BreakBeforeBraces: Custom # Attach
BraceWrapping:
AfterCaseLabel: true
AfterClass: false
AfterControlStatement: false
AfterEnum: false
AfterFunction: false
AfterNamespace: false
AfterObjCDeclaration: false
AfterStruct: false
AfterUnion: false
AfterExternBlock: false
BeforeCatch: false
BeforeElse: false
BeforeLambdaBody: false
BeforeWhile: false
IndentBraces: false
SplitEmptyFunction: false
SplitEmptyRecord: false
SplitEmptyNamespace: false
# BreakAdjacentStringLiterals: true
BreakAfterAttributes: Never
BreakBeforeBinaryOperators: None
BreakBeforeInlineASMColon: OnlyMultiline
BreakBeforeTernaryOperators: false
# BreakBinaryOperations: Never
BreakConstructorInitializers: AfterColon
# BreakFunctionDefinitionParameters: false
BreakInheritanceList: AfterComma
BreakStringLiterals: true
# BreakTemplateDeclarations: Yes
ColumnLimit: 120
CommentPragmas: '^ IWYU pragma:'
CompactNamespaces: false
ConstructorInitializerIndentWidth: 4
ContinuationIndentWidth: 4
Cpp11BracedListStyle: false
DerivePointerAlignment: false
DisableFormat: false
EmptyLineBeforeAccessModifier: Leave
EmptyLineAfterAccessModifier: Never
ExperimentalAutoDetectBinPacking: false
FixNamespaceComments: true
IncludeBlocks: Regroup
IncludeCategories:
- Regex: '".*"'
Priority: 1
SortPriority: 0
- Regex: '^<.*\.h>'
Priority: 2
SortPriority: 0
- Regex: '^<.*'
Priority: 3
SortPriority: 0
- Regex: '.*'
Priority: 4
SortPriority: 0
IncludeIsMainRegex: '([-_](test|unittest))?$'
IncludeIsMainSourceRegex: ''
IndentAccessModifiers: false
IndentCaseBlocks: true
IndentCaseLabels: true
IndentExternBlock: NoIndent
IndentGotoLabels: false
IndentPPDirectives: AfterHash
IndentWidth: 4
IndentWrappedFunctionNames: false
InsertBraces: true # NOTE: may lead to incorrect formatting
InsertNewlineAtEOF: true
JavaScriptQuotes: Leave
JavaScriptWrapImports: true
KeepEmptyLinesAtTheStartOfBlocks: false
LambdaBodyIndentation: Signature
LineEnding: LF
MacroBlockBegin: ''
MacroBlockEnd: ''
MaxEmptyLinesToKeep: 1
NamespaceIndentation: None
ObjCBinPackProtocolList: Auto
ObjCBlockIndentWidth: 4
ObjCSpaceAfterProperty: true
ObjCSpaceBeforeProtocolList: true
PPIndentWidth: -1
PackConstructorInitializers: CurrentLine
PenaltyBreakAssignment: 2
PenaltyBreakBeforeFirstCallParameter: 1
PenaltyBreakComment: 300
PenaltyBreakFirstLessLess: 120
PenaltyBreakString: 1000
PenaltyBreakTemplateDeclaration: 10
PenaltyExcessCharacter: 1000000
PenaltyReturnTypeOnItsOwnLine: 200
PointerAlignment: Middle
QualifierAlignment: Left
#QualifierOrder: ['static', 'inline', 'friend', 'constexpr', 'const', 'volatile', 'type', 'restrict']
RawStringFormats:
- Language: Cpp
Delimiters:
- cc
- CC
- cpp
- Cpp
- CPP
- 'c++'
- 'C++'
CanonicalDelimiter: ''
ReferenceAlignment: Middle
ReflowComments: false # IndentOnly
SeparateDefinitionBlocks: Always
SortIncludes: CaseInsensitive
SortUsingDeclarations: LexicographicNumeric
SpaceAfterCStyleCast: true
SpaceAfterLogicalNot: false
SpaceAfterTemplateKeyword: true
SpaceBeforeAssignmentOperators: true
SpaceBeforeCpp11BracedList: false
SpaceBeforeCtorInitializerColon: true
SpaceBeforeInheritanceColon: true
SpaceBeforeParens: ControlStatements
SpaceBeforeRangeBasedForLoopColon: true
SpaceInEmptyBlock: false
SpaceInEmptyParentheses: false
SpacesBeforeTrailingComments: 2
SpacesInAngles: Never
SpacesInContainerLiterals: true
SpacesInLineCommentPrefix:
Minimum: 1
Maximum: -1
SpacesInParentheses: false
SpacesInSquareBrackets: false
SpaceBeforeSquareBrackets: false
Standard: c++17
TabWidth: 4
UseTab: Never
WhitespaceSensitiveMacros: ['STRINGIZE']
...
.clang-tidy
+28
View File
@@ -0,0 +1,28 @@
---
Checks: >
bugprone-*,
-bugprone-easily-swappable-parameters,
-bugprone-implicit-widening-of-multiplication-result,
-bugprone-misplaced-widening-cast,
-bugprone-narrowing-conversions,
readability-*,
-readability-avoid-unconditional-preprocessor-if,
-readability-function-cognitive-complexity,
-readability-identifier-length,
-readability-implicit-bool-conversion,
-readability-magic-numbers,
-readability-uppercase-literal-suffix,
-readability-simplify-boolean-expr,
-readability-math-missing-parentheses,
clang-analyzer-*,
-clang-analyzer-security.insecureAPI.DeprecatedOrUnsafeBufferHandling,
performance-*,
-performance-enum-size,
portability-*,
-portability-simd-intrinsics,
misc-*,
-misc-const-correctness,
-misc-non-private-member-variables-in-classes,
-misc-no-recursion,
-misc-use-anonymous-namespace,
FormatStyle: none
.devops/cann.Dockerfile
+163
View File
@@ -0,0 +1,163 @@
# ==============================================================================
# ARGUMENTS
# ==============================================================================
# Define the CANN base image for easier version updates later
ARG CHIP_TYPE=910b
ARG CANN_BASE_IMAGE=quay.io/ascend/cann:8.5.0-${CHIP_TYPE}-openeuler24.03-py3.11
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
# ==============================================================================
# BUILD STAGE
# Compile all binary files and libraries
# ==============================================================================
ARG NODE_VERSION=24
FROM docker.io/node:$NODE_VERSION AS web
ARG APP_VERSION
WORKDIR /app/tools/ui
COPY tools/ui/package.json tools/ui/package-lock.json ./
RUN npm ci
COPY tools/ui/ ./
RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
FROM ${CANN_BASE_IMAGE} AS build
# -- Install build dependencies --
RUN yum install -y gcc g++ cmake make git openssl-devel python3 python3-pip && \
yum clean all && \
rm -rf /var/cache/yum
# -- Set the working directory --
WORKDIR /app
# -- Copy project files --
COPY . .
COPY --from=web /app/tools/ui/dist tools/ui/dist
# -- Set CANN environment variables (required for compilation) --
# Using ENV instead of `source` allows environment variables to persist across the entire image layer
ENV ASCEND_TOOLKIT_HOME=/usr/local/Ascend/ascend-toolkit/latest
ENV LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:${LD_LIBRARY_PATH}
ENV PATH=${ASCEND_TOOLKIT_HOME}/bin:${PATH}
ENV ASCEND_OPP_PATH=${ASCEND_TOOLKIT_HOME}/opp
ENV LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/runtime/lib64/stub:$LD_LIBRARY_PATH
# ... You can add other environment variables from the original file as needed ...
# For brevity, only core variables are listed here. You can paste the original ENV list here.
# -- Build llama.cpp --
# Use the passed CHIP_TYPE argument and add general build options
ARG CHIP_TYPE
RUN source /usr/local/Ascend/ascend-toolkit/set_env.sh --force \
&& \
cmake -B build \
-DGGML_CANN=ON \
-DCMAKE_BUILD_TYPE=Release \
-DSOC_TYPE=ascend${CHIP_TYPE} \
-DUSE_ACL_GRAPH=ON \
. && \
cmake --build build --config Release -j$(nproc)
# -- Organize build artifacts for copying in later stages --
# Create a lib directory to store all .so files
RUN mkdir -p /app/lib && \
find build -name "*.so*" -exec cp -P {} /app/lib \;
# Create a full directory to store all executables and Python scripts
RUN mkdir -p /app/full && \
cp build/bin/* /app/full/ && \
cp *.py /app/full/ && \
cp -r conversion /app/full/ && \
cp -r gguf-py /app/full/ && \
cp -r requirements /app/full/ && \
cp requirements.txt /app/full/
# If you have a tools.sh script, make sure it is copied here
# cp .devops/tools.sh /app/full/tools.sh
# ==============================================================================
# BASE STAGE
# Create a minimal base image with CANN runtime and common libraries
# ==============================================================================
FROM ${CANN_BASE_IMAGE} AS base
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
# -- Install runtime dependencies --
RUN yum install -y libgomp curl && \
yum clean all && \
rm -rf /var/cache/yum
# -- Set CANN environment variables (required for runtime) --
ENV ASCEND_TOOLKIT_HOME=/usr/local/Ascend/ascend-toolkit/latest
ENV LD_LIBRARY_PATH=/app:${ASCEND_TOOLKIT_HOME}/lib64:${LD_LIBRARY_PATH}
ENV PATH=${ASCEND_TOOLKIT_HOME}/bin:${PATH}
ENV ASCEND_OPP_PATH=${ASCEND_TOOLKIT_HOME}/opp
# ... You can add other environment variables from the original file as needed ...
WORKDIR /app
# Copy compiled .so files from the build stage
COPY --from=build /app/lib/ /app
# ==============================================================================
# FINAL STAGES (TARGETS)
# ==============================================================================
### Target: full
# Complete image with all tools, Python bindings, and dependencies
# ==============================================================================
FROM base AS full
COPY --from=build /app/full /app
# Install Python dependencies
RUN yum install -y git python3 python3-pip && \
pip3 install --no-cache-dir --upgrade pip setuptools wheel && \
pip3 install --no-cache-dir -r requirements.txt && \
yum clean all && \
rm -rf /var/cache/yum
# You need to provide a tools.sh script as the entrypoint
ENTRYPOINT ["/app/tools.sh"]
# If there is no tools.sh, you can set the default to start the server
# ENTRYPOINT ["/app/llama-server"]
### Target: light
# Lightweight image containing only llama-cli and llama-completion
# ==============================================================================
FROM base AS light
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
ENTRYPOINT [ "/app/llama-cli" ]
### Target: server
# Dedicated server image containing only llama-server
# ==============================================================================
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
COPY --from=build /app/full/llama /app/full/llama-server /app
HEALTHCHECK --interval=5m CMD [ "curl", "-f", "http://localhost:8080/health" ]
ENTRYPOINT [ "/app/llama-server" ]
.devops/cpu.Dockerfile
+124
View File
@@ -0,0 +1,124 @@
ARG UBUNTU_VERSION=24.04
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG NODE_VERSION=24
FROM docker.io/node:$NODE_VERSION AS web
ARG APP_VERSION
WORKDIR /app/tools/ui
COPY tools/ui/package.json tools/ui/package-lock.json ./
RUN npm ci
COPY tools/ui/ ./
RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
FROM docker.io/ubuntu:$UBUNTU_VERSION AS build
ARG TARGETARCH
RUN apt-get update && \
apt-get install -y gcc-14 g++-14 build-essential git cmake libssl-dev
ENV CC=gcc-14 CXX=g++-14
WORKDIR /app
COPY . .
COPY --from=web /app/tools/ui/dist tools/ui/dist
RUN if [ "$TARGETARCH" = "amd64" ] || [ "$TARGETARCH" = "arm64" ]; then \
cmake -S . -B build -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_TESTS=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON; \
else \
echo "Unsupported architecture"; \
exit 1; \
fi && \
cmake --build build -j $(nproc)
RUN mkdir -p /app/lib && \
find build -name "*.so*" -exec cp -P {} /app/lib \;
RUN mkdir -p /app/full \
&& cp build/bin/* /app/full \
&& cp *.py /app/full \
&& cp -r conversion /app/full \
&& cp -r gguf-py /app/full \
&& cp -r requirements /app/full \
&& cp requirements.txt /app/full \
&& cp .devops/tools.sh /app/full/tools.sh
## Base image
FROM docker.io/ubuntu:$UBUNTU_VERSION AS base
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
RUN apt-get update \
&& apt-get install -y libgomp1 curl ffmpeg \
&& apt autoremove -y \
&& apt clean -y \
&& rm -rf /tmp/* /var/tmp/* \
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
&& find /var/cache -type f -delete
COPY --from=build /app/lib/ /app
### Full
FROM base AS full
COPY --from=build /app/full /app
WORKDIR /app
RUN apt-get update \
&& apt-get install -y \
git \
python3 \
python3-pip \
python3-wheel \
&& pip install --break-system-packages --upgrade setuptools \
&& pip install --break-system-packages -r requirements.txt \
&& apt autoremove -y \
&& apt clean -y \
&& rm -rf /tmp/* /var/tmp/* \
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
&& find /var/cache -type f -delete
ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
WORKDIR /app
ENTRYPOINT [ "/app/llama-cli" ]
### Server, Server only
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
COPY --from=build /app/full/llama /app/full/llama-server /app
WORKDIR /app
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
ENTRYPOINT [ "/app/llama-server" ]
.devops/cuda.Dockerfile
+133
View File
@@ -0,0 +1,133 @@
ARG UBUNTU_VERSION=24.04
# This needs to generally match the container host's environment.
ARG CUDA_VERSION=12.8.1
ARG GCC_VERSION=14
# Target the CUDA build image
ARG BASE_CUDA_DEV_CONTAINER=docker.io/nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
ARG BASE_CUDA_RUN_CONTAINER=docker.io/nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG NODE_VERSION=24
FROM docker.io/node:$NODE_VERSION AS web
ARG APP_VERSION
WORKDIR /app/tools/ui
COPY tools/ui/package.json tools/ui/package-lock.json ./
RUN npm ci
COPY tools/ui/ ./
RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
FROM ${BASE_CUDA_DEV_CONTAINER} AS build
ARG GCC_VERSION
# CUDA architecture to build for (defaults to all supported archs)
ARG CUDA_DOCKER_ARCH=default
RUN apt-get update && \
apt-get install -y gcc-${GCC_VERSION} g++-${GCC_VERSION} build-essential cmake python3 python3-pip git libssl-dev libgomp1
ENV CC=gcc-${GCC_VERSION} CXX=g++-${GCC_VERSION} CUDAHOSTCXX=g++-${GCC_VERSION}
WORKDIR /app
COPY . .
COPY --from=web /app/tools/ui/dist tools/ui/dist
RUN if [ "${CUDA_DOCKER_ARCH}" != "default" ]; then \
export CMAKE_ARGS="-DCMAKE_CUDA_ARCHITECTURES=${CUDA_DOCKER_ARCH}"; \
fi && \
cmake -B build -DGGML_NATIVE=OFF -DGGML_CUDA=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_BUILD_TESTS=OFF ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
cmake --build build --config Release -j$(nproc)
RUN mkdir -p /app/lib && \
find build -name "*.so*" -exec cp -P {} /app/lib \;
RUN mkdir -p /app/full \
&& cp build/bin/* /app/full \
&& cp *.py /app/full \
&& cp -r conversion /app/full \
&& cp -r gguf-py /app/full \
&& cp -r requirements /app/full \
&& cp requirements.txt /app/full \
&& cp .devops/tools.sh /app/full/tools.sh
## Base image
FROM ${BASE_CUDA_RUN_CONTAINER} AS base
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
RUN apt-get update \
&& apt-get install -y libgomp1 curl ffmpeg \
&& apt autoremove -y \
&& apt clean -y \
&& rm -rf /tmp/* /var/tmp/* \
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
&& find /var/cache -type f -delete
COPY --from=build /app/lib/ /app
### Full
FROM base AS full
COPY --from=build /app/full /app
WORKDIR /app
RUN apt-get update \
&& apt-get install -y \
git \
python3 \
python3-pip \
python3-wheel \
&& pip install --break-system-packages --upgrade setuptools \
&& pip install --break-system-packages -r requirements.txt \
&& apt autoremove -y \
&& apt clean -y \
&& rm -rf /tmp/* /var/tmp/* \
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
&& find /var/cache -type f -delete
ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
WORKDIR /app
ENTRYPOINT [ "/app/llama-cli" ]
### Server, Server only
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
COPY --from=build /app/full/llama /app/full/llama-server /app
WORKDIR /app
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
ENTRYPOINT [ "/app/llama-server" ]
.devops/intel.Dockerfile
+162
View File
@@ -0,0 +1,162 @@
ARG ONEAPI_VERSION=2025.3.3-0-devel-ubuntu24.04
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
## Build Image
ARG NODE_VERSION=24
FROM docker.io/node:$NODE_VERSION AS web
ARG APP_VERSION
WORKDIR /app/tools/ui
COPY tools/ui/package.json tools/ui/package-lock.json ./
RUN npm ci
COPY tools/ui/ ./
RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
FROM docker.io/intel/deep-learning-essentials:$ONEAPI_VERSION AS build
ARG GGML_SYCL_F16=ON
ARG LEVEL_ZERO_VERSION=1.28.2
ARG LEVEL_ZERO_UBUNTU_VERSION=u24.04
RUN apt-get update && \
apt-get install -y git libssl-dev wget ca-certificates && \
cd /tmp && \
wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/level-zero_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O level-zero.deb && \
wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/level-zero-devel_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O level-zero-devel.deb && \
apt-get -o Dpkg::Options::="--force-overwrite" install -y ./level-zero.deb ./level-zero-devel.deb && \
rm -f /tmp/level-zero.deb /tmp/level-zero-devel.deb
WORKDIR /app
COPY . .
COPY --from=web /app/tools/ui/dist tools/ui/dist
RUN if [ "${GGML_SYCL_F16}" = "ON" ]; then \
echo "GGML_SYCL_F16 is set" \
&& export OPT_SYCL_F16="-DGGML_SYCL_F16=ON" \
&& export SYCL_PROGRAM_COMPILE_OPTIONS="-cl-fp32-correctly-rounded-divide-sqrt"; \
fi && \
echo "Building with dynamic libs" && \
cmake -B build -DGGML_NATIVE=OFF -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_BUILD_TESTS=OFF ${OPT_SYCL_F16} && \
cmake --build build --config Release -j$(nproc)
RUN mkdir -p /app/lib && \
find build -name "*.so*" -exec cp -P {} /app/lib \;
RUN mkdir -p /app/full \
&& cp build/bin/* /app/full \
&& cp *.py /app/full \
&& cp -r conversion /app/full \
&& cp -r gguf-py /app/full \
&& cp -r requirements /app/full \
&& cp requirements.txt /app/full \
&& cp .devops/tools.sh /app/full/tools.sh
FROM docker.io/intel/deep-learning-essentials:$ONEAPI_VERSION AS base
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
#Following versions are for multiple GPUs, since 26.x has known issue:
# https://github.com/ggml-org/llama.cpp/issues/21747,
# https://github.com/intel/compute-runtime/issues/921.
#ARG IGC_VERSION=v2.20.5
#ARG IGC_VERSION_FULL=2_2.20.5+19972
#ARG COMPUTE_RUNTIME_VERSION=25.40.35563.10
#ARG COMPUTE_RUNTIME_VERSION_FULL=25.40.35563.10-0
#ARG IGDGMM_VERSION=22.8.2
ARG IGC_VERSION=v2.34.4
ARG IGC_VERSION_FULL=2_2.34.4+21428
ARG COMPUTE_RUNTIME_VERSION=26.18.38308.1
ARG COMPUTE_RUNTIME_VERSION_FULL=26.18.38308.1-0
ARG IGDGMM_VERSION=22.10.0
RUN mkdir /tmp/neo/ && cd /tmp/neo/ \
&& wget https://github.com/intel/intel-graphics-compiler/releases/download/$IGC_VERSION/intel-igc-core-${IGC_VERSION_FULL}_amd64.deb \
&& wget https://github.com/intel/intel-graphics-compiler/releases/download/$IGC_VERSION/intel-igc-opencl-${IGC_VERSION_FULL}_amd64.deb \
&& wget https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/intel-ocloc-dbgsym_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.ddeb \
&& wget https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/intel-ocloc_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.deb \
&& wget https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/intel-opencl-icd-dbgsym_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.ddeb \
&& wget https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/intel-opencl-icd_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.deb \
&& wget https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/libigdgmm12_${IGDGMM_VERSION}_amd64.deb \
&& wget https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/libze-intel-gpu1-dbgsym_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.ddeb \
&& wget https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/libze-intel-gpu1_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.deb \
&& dpkg --install *.deb
RUN apt-get update \
&& apt-get install -y libgomp1 curl ffmpeg \
&& apt autoremove -y \
&& apt clean -y \
&& rm -rf /tmp/* /var/tmp/* \
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
&& find /var/cache -type f -delete
### Full
FROM base AS full
COPY --from=build /app/lib/ /app
COPY --from=build /app/full /app
WORKDIR /app
RUN apt-get update && \
apt-get install -y \
git \
python3 \
python3-pip \
python3-venv && \
python3 -m venv /opt/venv && \
. /opt/venv/bin/activate && \
pip install --upgrade pip setuptools wheel && \
pip install -r requirements.txt && \
apt autoremove -y && \
apt clean -y && \
rm -rf /tmp/* /var/tmp/* && \
find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete && \
find /var/cache -type f -delete
ENV PATH="/opt/venv/bin:$PATH"
ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light
COPY --from=build /app/lib/ /app
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
WORKDIR /app
ENTRYPOINT [ "/app/llama-cli" ]
### Server, Server only
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
COPY --from=build /app/lib/ /app
COPY --from=build /app/full/llama /app/full/llama-server /app
WORKDIR /app
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
ENTRYPOINT [ "/app/llama-server" ]
.devops/llama-cli-cann.Dockerfile
+62
View File
@@ -0,0 +1,62 @@
ARG ASCEND_VERSION=8.5.0-910b-openeuler22.03-py3.10
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
FROM docker.io/ascendai/cann:$ASCEND_VERSION AS build
WORKDIR /app
COPY . .
RUN yum install -y gcc g++ cmake make openssl-devel
ENV ASCEND_TOOLKIT_HOME=/usr/local/Ascend/ascend-toolkit/latest
ENV LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:$LIBRARY_PATH
ENV LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:${ASCEND_TOOLKIT_HOME}/lib64/plugin/opskernel:${ASCEND_TOOLKIT_HOME}/lib64/plugin/nnengine:${ASCEND_TOOLKIT_HOME}/opp/built-in/op_impl/ai_core/tbe/op_tiling:${LD_LIBRARY_PATH}
ENV PYTHONPATH=${ASCEND_TOOLKIT_HOME}/python/site-packages:${ASCEND_TOOLKIT_HOME}/opp/built-in/op_impl/ai_core/tbe:${PYTHONPATH}
ENV PATH=${ASCEND_TOOLKIT_HOME}/bin:${ASCEND_TOOLKIT_HOME}/compiler/ccec_compiler/bin:${PATH}
ENV ASCEND_AICPU_PATH=${ASCEND_TOOLKIT_HOME}
ENV ASCEND_OPP_PATH=${ASCEND_TOOLKIT_HOME}/opp
ENV TOOLCHAIN_HOME=${ASCEND_TOOLKIT_HOME}/toolkit
ENV ASCEND_HOME_PATH=${ASCEND_TOOLKIT_HOME}
# find libascend_hal.so, because the drive hasn`t been mounted.
ENV LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/runtime/lib64/stub:$LD_LIBRARY_PATH
RUN echo "Building with static libs" && \
source /usr/local/Ascend/ascend-toolkit/set_env.sh --force && \
cmake -B build -DGGML_NATIVE=OFF -DGGML_CANN=ON -DBUILD_SHARED_LIBS=OFF -DLLAMA_BUILD_TESTS=OFF && \
cmake --build build --config Release --target llama-cli && \
cmake --build build --config Release --target llama-completion
# TODO: use image with NNRT
FROM docker.io/ascendai/cann:$ASCEND_VERSION AS runtime
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
COPY --from=build /app/build/bin/llama-cli /app/build/bin/llama-completion /
ENV LC_ALL=C.utf8
ENV ASCEND_TOOLKIT_HOME=/usr/local/Ascend/ascend-toolkit/latest
ENV LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:$LIBRARY_PATH
ENV LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:${ASCEND_TOOLKIT_HOME}/lib64/plugin/opskernel:${ASCEND_TOOLKIT_HOME}/lib64/plugin/nnengine:${ASCEND_TOOLKIT_HOME}/opp/built-in/op_impl/ai_core/tbe/op_tiling:${LD_LIBRARY_PATH}
ENV PYTHONPATH=${ASCEND_TOOLKIT_HOME}/python/site-packages:${ASCEND_TOOLKIT_HOME}/opp/built-in/op_impl/ai_core/tbe:${PYTHONPATH}
ENV PATH=${ASCEND_TOOLKIT_HOME}/bin:${ASCEND_TOOLKIT_HOME}/compiler/ccec_compiler/bin:${PATH}
ENV ASCEND_AICPU_PATH=${ASCEND_TOOLKIT_HOME}
ENV ASCEND_OPP_PATH=${ASCEND_TOOLKIT_HOME}/opp
ENV TOOLCHAIN_HOME=${ASCEND_TOOLKIT_HOME}/toolkit
ENV ASCEND_HOME_PATH=${ASCEND_TOOLKIT_HOME}
ENTRYPOINT ["/llama-cli" ]
.devops/llama-cpp-cuda.srpm.spec
+85
View File
@@ -0,0 +1,85 @@
# SRPM for building from source and packaging an RPM for RPM-based distros.
# https://docs.fedoraproject.org/en-US/quick-docs/creating-rpm-packages
# Built and maintained by John Boero - boeroboy@gmail.com
# In honor of Seth Vidal https://www.redhat.com/it/blog/thank-you-seth-vidal
# Notes for llama.cpp:
# 1. Tags are currently based on hash - which will not sort asciibetically.
# We need to declare standard versioning if people want to sort latest releases.
# 2. Builds for CUDA/OpenCL support are separate, with different depenedencies.
# 3. NVidia's developer repo must be enabled with nvcc, cublas, clblas, etc installed.
# Example: https://developer.download.nvidia.com/compute/cuda/repos/fedora37/x86_64/cuda-fedora37.repo
# 4. OpenCL/CLBLAST support simply requires the ICD loader and basic opencl libraries.
# It is up to the user to install the correct vendor-specific support.
Name: llama.cpp-cuda
Version: %( date "+%%Y%%m%%d" )
Release: 1%{?dist}
Summary: CPU Inference of LLaMA model in pure C/C++ (no CUDA/OpenCL)
License: MIT
Source0: https://github.com/ggml-org/llama.cpp/archive/refs/heads/master.tar.gz
BuildRequires: coreutils make gcc-c++ git cuda-toolkit
Requires: cuda-toolkit
URL: https://github.com/ggml-org/llama.cpp
%define debug_package %{nil}
%define source_date_epoch_from_changelog 0
%description
CPU inference for Meta's Lllama2 models using default options.
%prep
%setup -n llama.cpp-master
%build
make -j GGML_CUDA=1
%install
mkdir -p %{buildroot}%{_bindir}/
cp -p llama-cli %{buildroot}%{_bindir}/llama-cuda-cli
cp -p llama-completion %{buildroot}%{_bindir}/llama-cuda-completion
cp -p llama-server %{buildroot}%{_bindir}/llama-cuda-server
cp -p llama-simple %{buildroot}%{_bindir}/llama-cuda-simple
mkdir -p %{buildroot}/usr/lib/systemd/system
%{__cat} <<EOF > %{buildroot}/usr/lib/systemd/system/llamacuda.service
[Unit]
Description=Llama.cpp server, CPU only (no GPU support in this build).
After=syslog.target network.target local-fs.target remote-fs.target nss-lookup.target
[Service]
Type=simple
EnvironmentFile=/etc/sysconfig/llama
ExecStart=/usr/bin/llama-cuda-server $LLAMA_ARGS
ExecReload=/bin/kill -s HUP $MAINPID
Restart=never
[Install]
WantedBy=default.target
EOF
mkdir -p %{buildroot}/etc/sysconfig
%{__cat} <<EOF > %{buildroot}/etc/sysconfig/llama
LLAMA_ARGS="-m /opt/llama2/ggml-model-f32.bin"
EOF
%clean
rm -rf %{buildroot}
rm -rf %{_builddir}/*
%files
%{_bindir}/llama-cuda-cli
%{_bindir}/llama-cuda-completion
%{_bindir}/llama-cuda-server
%{_bindir}/llama-cuda-simple
/usr/lib/systemd/system/llamacuda.service
%config /etc/sysconfig/llama
%pre
%post
%preun
%postun
%changelog
.devops/llama-cpp.srpm.spec
+87
View File
@@ -0,0 +1,87 @@
# SRPM for building from source and packaging an RPM for RPM-based distros.
# https://docs.fedoraproject.org/en-US/quick-docs/creating-rpm-packages
# Built and maintained by John Boero - boeroboy@gmail.com
# In honor of Seth Vidal https://www.redhat.com/it/blog/thank-you-seth-vidal
# Notes for llama.cpp:
# 1. Tags are currently based on hash - which will not sort asciibetically.
# We need to declare standard versioning if people want to sort latest releases.
# In the meantime, YYYYMMDD format will be used.
# 2. Builds for CUDA/OpenCL support are separate, with different depenedencies.
# 3. NVidia's developer repo must be enabled with nvcc, cublas, clblas, etc installed.
# Example: https://developer.download.nvidia.com/compute/cuda/repos/fedora37/x86_64/cuda-fedora37.repo
# 4. OpenCL/CLBLAST support simply requires the ICD loader and basic opencl libraries.
# It is up to the user to install the correct vendor-specific support.
Name: llama.cpp
Version: %( date "+%%Y%%m%%d" )
Release: 1%{?dist}
Summary: CPU Inference of LLaMA model in pure C/C++ (no CUDA/OpenCL)
License: MIT
Source0: https://github.com/ggml-org/llama.cpp/archive/refs/heads/master.tar.gz
BuildRequires: coreutils make gcc-c++ git libstdc++-devel
Requires: libstdc++
URL: https://github.com/ggml-org/llama.cpp
%define debug_package %{nil}
%define source_date_epoch_from_changelog 0
%description
CPU inference for Meta's Lllama2 models using default options.
Models are not included in this package and must be downloaded separately.
%prep
%setup -n llama.cpp-master
%build
make -j
%install
mkdir -p %{buildroot}%{_bindir}/
cp -p llama-cli %{buildroot}%{_bindir}/llama-cli
cp -p llama-completion %{buildroot}%{_bindir}/llama-completion
cp -p llama-server %{buildroot}%{_bindir}/llama-server
cp -p llama-simple %{buildroot}%{_bindir}/llama-simple
mkdir -p %{buildroot}/usr/lib/systemd/system
%{__cat} <<EOF > %{buildroot}/usr/lib/systemd/system/llama.service
[Unit]
Description=Llama.cpp server, CPU only (no GPU support in this build).
After=syslog.target network.target local-fs.target remote-fs.target nss-lookup.target
[Service]
Type=simple
EnvironmentFile=/etc/sysconfig/llama
ExecStart=/usr/bin/llama-server $LLAMA_ARGS
ExecReload=/bin/kill -s HUP $MAINPID
Restart=never
[Install]
WantedBy=default.target
EOF
mkdir -p %{buildroot}/etc/sysconfig
%{__cat} <<EOF > %{buildroot}/etc/sysconfig/llama
LLAMA_ARGS="-m /opt/llama2/ggml-model-f32.bin"
EOF
%clean
rm -rf %{buildroot}
rm -rf %{_builddir}/*
%files
%{_bindir}/llama-cli
%{_bindir}/llama-completion
%{_bindir}/llama-server
%{_bindir}/llama-simple
/usr/lib/systemd/system/llama.service
%config /etc/sysconfig/llama
%pre
%post
%preun
%postun
%changelog
.devops/musa.Dockerfile
+135
View File
@@ -0,0 +1,135 @@
ARG UBUNTU_VERSION=22.04
# This needs to generally match the container host's environment.
ARG MUSA_VERSION=rc4.3.0
# Target the MUSA build image
ARG BASE_MUSA_DEV_CONTAINER=docker.io/mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_VERSION}-amd64
ARG BASE_MUSA_RUN_CONTAINER=docker.io/mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}-amd64
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG NODE_VERSION=24
FROM docker.io/node:$NODE_VERSION AS web
ARG APP_VERSION
WORKDIR /app/tools/ui
COPY tools/ui/package.json tools/ui/package-lock.json ./
RUN npm ci
COPY tools/ui/ ./
RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
FROM ${BASE_MUSA_DEV_CONTAINER} AS build
# MUSA architecture to build for (defaults to all supported archs)
ARG MUSA_DOCKER_ARCH=default
RUN apt-get update && \
apt-get install -y \
build-essential \
cmake \
python3 \
python3-pip \
git \
libssl-dev \
libgomp1
WORKDIR /app
COPY . .
COPY --from=web /app/tools/ui/dist tools/ui/dist
RUN if [ "${MUSA_DOCKER_ARCH}" != "default" ]; then \
export CMAKE_ARGS="-DMUSA_ARCHITECTURES=${MUSA_DOCKER_ARCH}"; \
fi && \
cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_BUILD_TESTS=OFF ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
cmake --build build --config Release -j$(nproc)
RUN mkdir -p /app/lib && \
find build -name "*.so*" -exec cp -P {} /app/lib \;
RUN mkdir -p /app/full \
&& cp build/bin/* /app/full \
&& cp *.py /app/full \
&& cp -r conversion /app/full \
&& cp -r gguf-py /app/full \
&& cp -r requirements /app/full \
&& cp requirements.txt /app/full \
&& cp .devops/tools.sh /app/full/tools.sh
## Base image
FROM ${BASE_MUSA_RUN_CONTAINER} AS base
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
RUN apt-get update \
&& apt-get install -y libgomp1 curl ffmpeg \
&& apt autoremove -y \
&& apt clean -y \
&& rm -rf /tmp/* /var/tmp/* \
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
&& find /var/cache -type f -delete
COPY --from=build /app/lib/ /app
### Full
FROM base AS full
COPY --from=build /app/full /app
WORKDIR /app
RUN apt-get update \
&& apt-get install -y \
git \
python3 \
python3-pip \
&& pip install --upgrade pip setuptools wheel \
&& pip install -r requirements.txt \
&& apt autoremove -y \
&& apt clean -y \
&& rm -rf /tmp/* /var/tmp/* \
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
&& find /var/cache -type f -delete
ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
WORKDIR /app
ENTRYPOINT [ "/app/llama-cli" ]
### Server, Server only
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
COPY --from=build /app/full/llama /app/full/llama-server /app
WORKDIR /app
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
ENTRYPOINT [ "/app/llama-server" ]
.devops/nix/apps.nix
+21
View File
@@ -0,0 +1,21 @@
{
perSystem =
{ config, lib, ... }:
{
apps =
let
inherit (config.packages) default;
binaries = [
"llama-cli"
"llama-embedding"
"llama-server"
"llama-quantize"
];
mkApp = name: {
type = "app";
program = "${default}/bin/${name}";
};
in
lib.genAttrs binaries mkApp;
};
}
.devops/nix/devshells.nix
+52
View File
@@ -0,0 +1,52 @@
{ inputs, ... }:
{
perSystem =
{
config,
lib,
system,
...
}:
{
devShells =
let
pkgs = import inputs.nixpkgs { inherit system; };
stdenv = pkgs.stdenv;
scripts = config.packages.python-scripts;
in
lib.pipe (config.packages) [
(lib.concatMapAttrs (
name: package: {
${name} = pkgs.mkShell {
name = "${name}";
inputsFrom = [ package ];
shellHook = ''
echo "Entering ${name} devShell"
'';
};
"${name}-extra" =
if (name == "python-scripts") then
null
else
pkgs.mkShell {
name = "${name}-extra";
inputsFrom = [
package
scripts
];
# Extra packages that *may* be used by some scripts
packages = [
pkgs.python3Packages.tiktoken
];
shellHook = ''
echo "Entering ${name} devShell"
addToSearchPath "LD_LIBRARY_PATH" "${lib.getLib stdenv.cc.cc}/lib"
'';
};
}
))
(lib.filterAttrs (name: value: value != null))
];
};
}
.devops/nix/docker.nix
+37
View File
@@ -0,0 +1,37 @@
{
lib,
dockerTools,
buildEnv,
llama-cpp,
interactive ? true,
coreutils,
}:
# A tar that can be fed into `docker load`:
#
# $ nix build .#llamaPackages.docker
# $ docker load < result
# For details and variations cf.
# - https://nixos.org/manual/nixpkgs/unstable/#ssec-pkgs-dockerTools-buildLayeredImage
# - https://discourse.nixos.org/t/a-faster-dockertools-buildimage-prototype/16922
# - https://nixery.dev/
# Approximate (compressed) sizes, at the time of writing, are:
#
# .#llamaPackages.docker: 125M;
# .#llamaPackagesCuda.docker: 537M;
# .#legacyPackages.aarch64-linux.llamaPackagesXavier.docker: 415M.
dockerTools.buildLayeredImage {
name = llama-cpp.pname;
tag = "latest";
contents =
[ llama-cpp ]
++ lib.optionals interactive [
coreutils
dockerTools.binSh
dockerTools.caCertificates
];
}
.devops/nix/jetson-support.nix
+39
View File
@@ -0,0 +1,39 @@
{ inputs, ... }:
{
perSystem =
{
config,
system,
lib,
pkgsCuda,
...
}:
{
legacyPackages =
let
caps.llamaPackagesXavier = "7.2";
caps.llamaPackagesOrin = "8.7";
caps.llamaPackagesTX2 = "6.2";
caps.llamaPackagesNano = "5.3";
pkgsFor =
cap:
import inputs.nixpkgs {
inherit system;
config = {
cudaSupport = true;
cudaCapabilities = [ cap ];
cudaEnableForwardCompat = false;
inherit (pkgsCuda.config) allowUnfreePredicate;
};
};
in
builtins.mapAttrs (name: cap: (pkgsFor cap).callPackage ./scope.nix { }) caps;
packages = lib.optionalAttrs (system == "aarch64-linux") {
jetson-xavier = config.legacyPackages.llamaPackagesXavier.llama-cpp;
jetson-orin = config.legacyPackages.llamaPackagesOrin.llama-cpp;
jetson-nano = config.legacyPackages.llamaPackagesNano.llama-cpp;
};
};
}
.devops/nix/nixpkgs-instances.nix
+45
View File
@@ -0,0 +1,45 @@
{ inputs, ... }:
{
# The _module.args definitions are passed on to modules as arguments. E.g.
# the module `{ pkgs ... }: { /* config */ }` implicitly uses
# `_module.args.pkgs` (defined in this case by flake-parts).
perSystem =
{ lib, system, ... }:
{
_module.args = {
# Note: bringing up https://zimbatm.com/notes/1000-instances-of-nixpkgs
# again, the below creates several nixpkgs instances which the
# flake-centric CLI will be forced to evaluate e.g. on `nix flake show`.
#
# This is currently "slow" and "expensive", on a certain scale.
# This also isn't "right" in that this hinders dependency injection at
# the level of flake inputs. This might get removed in the foreseeable
# future.
#
# Note that you can use these expressions without Nix
# (`pkgs.callPackage ./devops/nix/scope.nix { }` is the entry point).
pkgsCuda = import inputs.nixpkgs {
inherit system;
# Ensure dependencies use CUDA consistently (e.g. that openmpi, ucc,
# and ucx are built with CUDA support)
config.cudaSupport = true;
config.allowUnfreePredicate =
p:
builtins.all (
license:
license.free
|| builtins.elem license.shortName [
"CUDA EULA"
"cuDNN EULA"
]
) (p.meta.licenses or (lib.toList p.meta.license));
};
# Ensure dependencies use ROCm consistently
pkgsRocm = import inputs.nixpkgs {
inherit system;
config.rocmSupport = true;
};
};
};
}
.devops/nix/package-gguf-py.nix
+38
View File
@@ -0,0 +1,38 @@
{
lib,
llamaVersion,
numpy,
tqdm,
requests,
sentencepiece,
pyyaml,
poetry-core,
buildPythonPackage,
pytestCheckHook,
}:
buildPythonPackage {
pname = "gguf";
version = llamaVersion;
pyproject = true;
nativeBuildInputs = [ poetry-core ];
propagatedBuildInputs = [
numpy
tqdm
sentencepiece
pyyaml
requests
];
src = lib.cleanSource ../../gguf-py;
pythonImportsCheck = [
"numpy"
"gguf"
];
nativeCheckInputs = [ pytestCheckHook ];
doCheck = true;
meta = with lib; {
description = "Python package for writing binary files in the GGUF format";
license = licenses.mit;
maintainers = [ maintainers.ditsuke ];
};
}
.devops/nix/package.nix
+275
View File
@@ -0,0 +1,275 @@
{
lib,
glibc,
config,
stdenv,
stdenvNoCC,
runCommand,
cmake,
ninja,
pkg-config,
git,
mpi,
blas,
cudaPackages,
autoAddDriverRunpath,
darwin,
rocmPackages,
vulkan-headers,
vulkan-loader,
openssl,
shaderc,
spirv-headers,
nodejs,
importNpmLock,
useBlas ?
builtins.all (x: !x) [
useCuda
useMetalKit
useRocm
useVulkan
]
&& blas.meta.available,
useCuda ? config.cudaSupport,
useMetalKit ? stdenv.isAarch64 && stdenv.isDarwin,
# Increases the runtime closure size by ~700M
useMpi ? false,
useRocm ? config.rocmSupport,
rocmGpuTargets ? builtins.concatStringsSep ";" rocmPackages.clr.gpuTargets,
useVulkan ? false,
useRpc ? false,
llamaVersion ? "0.0.0", # Arbitrary version, substituted by the flake
# It's necessary to consistently use backendStdenv when building with CUDA support,
# otherwise we get libstdc++ errors downstream.
effectiveStdenv ? if useCuda then cudaPackages.backendStdenv else stdenv,
enableStatic ? effectiveStdenv.hostPlatform.isStatic,
precompileMetalShaders ? false,
useWebUi ? true,
}:
let
inherit (lib)
cmakeBool
cmakeFeature
optionalAttrs
optionals
strings
;
stdenv = throw "Use effectiveStdenv instead";
suffices =
lib.optionals useBlas [ "BLAS" ]
++ lib.optionals useCuda [ "CUDA" ]
++ lib.optionals useMetalKit [ "MetalKit" ]
++ lib.optionals useMpi [ "MPI" ]
++ lib.optionals useRocm [ "ROCm" ]
++ lib.optionals useVulkan [ "Vulkan" ];
pnameSuffix =
strings.optionalString (suffices != [ ])
"-${strings.concatMapStringsSep "-" strings.toLower suffices}";
descriptionSuffix = strings.optionalString (
suffices != [ ]
) ", accelerated with ${strings.concatStringsSep ", " suffices}";
xcrunHost = runCommand "xcrunHost" { } ''
mkdir -p $out/bin
ln -s /usr/bin/xcrun $out/bin
'';
# apple_sdk is supposed to choose sane defaults, no need to handle isAarch64
# separately
darwinBuildInputs =
with darwin.apple_sdk.frameworks;
[
Accelerate
CoreVideo
CoreGraphics
]
++ optionals useMetalKit [ MetalKit ];
cudaBuildInputs = with cudaPackages; [
cuda_cudart
cuda_cccl # <nv/target>
libcublas
];
rocmBuildInputs = with rocmPackages; [
clr
hipblas
rocblas
];
vulkanBuildInputs = [
vulkan-headers
vulkan-loader
shaderc
spirv-headers
];
in
effectiveStdenv.mkDerivation (finalAttrs: {
pname = "llama-cpp${pnameSuffix}";
version = llamaVersion;
# Note: none of the files discarded here are visible in the sandbox or
# affect the output hash. This also means they can be modified without
# triggering a rebuild.
src = lib.cleanSourceWith {
filter =
name: type:
let
noneOf = builtins.all (x: !x);
baseName = baseNameOf name;
in
noneOf [
(lib.hasSuffix ".nix" name) # Ignore *.nix files when computing outPaths
(lib.hasSuffix ".md" name) # Ignore *.md changes whe computing outPaths
(lib.hasPrefix "." baseName) # Skip hidden files and directories
(baseName == "flake.lock")
];
src = lib.cleanSource ../../.;
};
# Builds the webui locally, taking care not to require updating any sha256 hash.
webui = stdenvNoCC.mkDerivation {
pname = "webui";
version = llamaVersion;
src = lib.cleanSource ../../tools/ui;
nativeBuildInputs = [
nodejs
importNpmLock.linkNodeModulesHook
];
# no sha256 required when using buildNodeModules
npmDeps = importNpmLock.buildNodeModules {
npmRoot = ../../tools/ui;
inherit nodejs;
};
installPhase = ''
LLAMA_UI_OUT_DIR=$out npm run build --offline
'';
};
postPatch = lib.optionalString useWebUi ''
cp -r ${finalAttrs.webui} tools/ui/dist
chmod -R u+w tools/ui/dist
'';
# With PR#6015 https://github.com/ggml-org/llama.cpp/pull/6015,
# `default.metallib` may be compiled with Metal compiler from XCode
# and we need to escape sandbox on MacOS to access Metal compiler.
# `xcrun` is used find the path of the Metal compiler, which is varible
# and not on $PATH
# see https://github.com/ggml-org/llama.cpp/pull/6118 for discussion
__noChroot = effectiveStdenv.isDarwin && useMetalKit && precompileMetalShaders;
nativeBuildInputs =
[
cmake
ninja
pkg-config
git
]
++ optionals useCuda [
cudaPackages.cuda_nvcc
autoAddDriverRunpath
]
++ optionals (effectiveStdenv.hostPlatform.isGnu && enableStatic) [ glibc.static ]
++ optionals (effectiveStdenv.isDarwin && useMetalKit && precompileMetalShaders) [ xcrunHost ];
buildInputs =
optionals effectiveStdenv.isDarwin darwinBuildInputs
++ optionals useCuda cudaBuildInputs
++ optionals useMpi [ mpi ]
++ optionals useRocm rocmBuildInputs
++ optionals useBlas [ blas ]
++ optionals useVulkan vulkanBuildInputs
++ [ openssl ];
cmakeFlags =
[
(cmakeBool "LLAMA_BUILD_SERVER" true)
(cmakeBool "LLAMA_BUILD_WEBUI" useWebUi)
(cmakeBool "BUILD_SHARED_LIBS" (!enableStatic))
(cmakeBool "CMAKE_SKIP_BUILD_RPATH" true)
(cmakeBool "GGML_NATIVE" false)
(cmakeBool "GGML_BLAS" useBlas)
(cmakeBool "GGML_CUDA" useCuda)
(cmakeBool "GGML_HIP" useRocm)
(cmakeBool "GGML_METAL" useMetalKit)
(cmakeBool "GGML_VULKAN" useVulkan)
(cmakeBool "GGML_STATIC" enableStatic)
(cmakeBool "GGML_RPC" useRpc)
]
++ optionals useCuda [
(
with cudaPackages.flags;
cmakeFeature "CMAKE_CUDA_ARCHITECTURES" (
builtins.concatStringsSep ";" (map dropDot cudaCapabilities)
)
)
]
++ optionals useRocm [
(cmakeFeature "CMAKE_HIP_COMPILER" "${rocmPackages.llvm.clang}/bin/clang")
(cmakeFeature "CMAKE_HIP_ARCHITECTURES" rocmGpuTargets)
]
++ optionals useMetalKit [
(lib.cmakeFeature "CMAKE_C_FLAGS" "-D__ARM_FEATURE_DOTPROD=1")
(cmakeBool "GGML_METAL_EMBED_LIBRARY" (!precompileMetalShaders))
];
# Environment variables needed for ROCm
env = optionalAttrs useRocm {
ROCM_PATH = "${rocmPackages.clr}";
HIP_DEVICE_LIB_PATH = "${rocmPackages.rocm-device-libs}/amdgcn/bitcode";
};
# TODO(SomeoneSerge): It's better to add proper install targets at the CMake level,
# if they haven't been added yet.
postInstall = ''
mkdir -p $out/include
cp $src/include/llama.h $out/include/
'';
meta = {
# Configurations we don't want even the CI to evaluate. Results in the
# "unsupported platform" messages. This is mostly a no-op, because
# cudaPackages would've refused to evaluate anyway.
badPlatforms = optionals useCuda lib.platforms.darwin;
# Configurations that are known to result in build failures. Can be
# overridden by importing Nixpkgs with `allowBroken = true`.
broken = (useMetalKit && !effectiveStdenv.isDarwin);
description = "Inference of LLaMA model in pure C/C++${descriptionSuffix}";
homepage = "https://github.com/ggml-org/llama.cpp/";
license = lib.licenses.mit;
# Accommodates `nix run` and `lib.getExe`
mainProgram = "llama-cli";
# These people might respond, on the best effort basis, if you ping them
# in case of Nix-specific regressions or for reviewing Nix-specific PRs.
# Consider adding yourself to this list if you want to ensure this flake
# stays maintained and you're willing to invest your time. Do not add
# other people without their consent. Consider removing people after
# they've been unreachable for long periods of time.
# Note that lib.maintainers is defined in Nixpkgs, but you may just add
# an attrset following the same format as in
# https://github.com/NixOS/nixpkgs/blob/f36a80e54da29775c78d7eff0e628c2b4e34d1d7/maintainers/maintainer-list.nix
maintainers = with lib.maintainers; [
philiptaron
SomeoneSerge
];
# Extend `badPlatforms` instead
platforms = lib.platforms.all;
};
})
.devops/nix/python-scripts.nix
+66
View File
@@ -0,0 +1,66 @@
{
lib,
stdenv,
buildPythonPackage,
poetry-core,
mkShell,
python3Packages,
gguf-py,
}@inputs:
let
llama-python-deps = with python3Packages; [
numpy
sentencepiece
transformers
protobuf
torchWithoutCuda
gguf-py
tqdm
# for scripts/compare-llama-bench.py
gitpython
tabulate
# for examples/pydantic-models-to-grammar-examples.py
docstring-parser
pydantic
];
llama-python-test-deps = with python3Packages; [
# Server bench
matplotlib
# server tests
openai
pytest
prometheus-client
];
in
buildPythonPackage ({
pname = "llama-scripts";
version = "0.0.0";
pyproject = true;
# NOTE: The files filtered out here are not visible in the build sandbox, neither
# do they affect the output hash. They can be modified without triggering a rebuild.
src = lib.cleanSourceWith {
filter =
name: type:
let
any = builtins.any (x: x);
baseName = builtins.baseNameOf name;
in
any [
(lib.hasSuffix ".py" name)
(baseName == "README.md")
(baseName == "pyproject.toml")
];
src = lib.cleanSource ../../.;
};
nativeBuildInputs = [ poetry-core ];
nativeCheckInputs = llama-python-test-deps;
dependencies = llama-python-deps;
})
.devops/nix/scope.nix
+35
View File
@@ -0,0 +1,35 @@
{
lib,
newScope,
python3,
llamaVersion ? "0.0.0",
}:
let
pythonPackages = python3.pkgs;
in
# We're using `makeScope` instead of just writing out an attrset
# because it allows users to apply overlays later using `overrideScope'`.
# Cf. https://noogle.dev/f/lib/makeScope
lib.makeScope newScope (self: {
inherit llamaVersion;
gguf-py = self.callPackage ./package-gguf-py.nix {
inherit (pythonPackages)
numpy
tqdm
sentencepiece
pyyaml
pytestCheckHook
requests
buildPythonPackage
poetry-core
;
};
python-scripts = self.callPackage ./python-scripts.nix { inherit (pythonPackages) buildPythonPackage poetry-core; };
llama-cpp = self.callPackage ./package.nix { };
docker = self.callPackage ./docker.nix { };
docker-min = self.callPackage ./docker.nix { interactive = false; };
sif = self.callPackage ./sif.nix { };
})
.devops/nix/sif.nix
+27
View File
@@ -0,0 +1,27 @@
{
lib,
singularity-tools,
llama-cpp,
bashInteractive,
interactive ? false,
}:
let
optionalInt = cond: x: if cond then x else 0;
in
singularity-tools.buildImage rec {
inherit (llama-cpp) name;
contents = [ llama-cpp ] ++ lib.optionals interactive [ bashInteractive ];
# These are excessive (but safe) for most variants. Building singularity
# images requires superuser privileges, so we build them inside a VM in a
# writable image of pre-determined size.
#
# ROCm is currently affected by https://github.com/NixOS/nixpkgs/issues/276846
#
# Expected image sizes:
# - cpu/blas: 150M,
# - cuda, all gencodes: 560M,
diskSize = 4096 + optionalInt llama-cpp.useRocm 16384;
memSize = diskSize;
}
.devops/openvino.Dockerfile
+234
View File
@@ -0,0 +1,234 @@
ARG OPENVINO_VERSION_MAJOR=2026.2.1
ARG OPENVINO_VERSION_FULL=2026.2.1.21919.ede283a88e3
ARG UBUNTU_VERSION=24.04
# Intel GPU driver versions. https://github.com/intel/compute-runtime/releases
ARG IGC_VERSION=v2.36.3
ARG IGC_VERSION_FULL=2_2.36.3+21719
ARG COMPUTE_RUNTIME_VERSION=26.22.38646.4
ARG COMPUTE_RUNTIME_VERSION_FULL=26.22.38646.4-0
ARG IGDGMM_VERSION=22.10.0
# Intel NPU driver versions. https://github.com/intel/linux-npu-driver/releases
ARG NPU_DRIVER_VERSION=v1.33.0
ARG NPU_DRIVER_FULL=v1.33.0.20260529-26625960453
ARG LIBZE1_VERSION=1.27.0-1~24.04~ppa2
# Optional proxy build arguments
ARG http_proxy=
ARG https_proxy=
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG NODE_VERSION=24
FROM docker.io/node:$NODE_VERSION AS web
ARG APP_VERSION
WORKDIR /app/tools/ui
COPY tools/ui/package.json tools/ui/package-lock.json ./
RUN npm ci
COPY tools/ui/ ./
RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
## Build Image
FROM docker.io/ubuntu:${UBUNTU_VERSION} AS build
# Pass proxy args to build stage
ARG http_proxy
ARG https_proxy
RUN apt-get update && \
apt-get install -y --no-install-recommends \
ca-certificates \
gnupg \
wget \
git \
cmake \
ninja-build \
build-essential \
libtbb12 \
libssl-dev \
ocl-icd-opencl-dev \
opencl-headers \
opencl-clhpp-headers \
intel-opencl-icd && \
rm -rf /var/lib/apt/lists/*
# OpenVINO toolkit and GPU/NPU drivers are cached via BuildKit cache mounts to avoid re-downloading on rebuilds.
# Install OpenVINO for Ubuntu 24.04.
ARG OPENVINO_VERSION_MAJOR
ARG OPENVINO_VERSION_FULL
RUN --mount=type=cache,target=/var/cache/openvino,sharing=locked \
mkdir -p /opt/intel && \
TGZ=/var/cache/openvino/openvino_toolkit_ubuntu24_${OPENVINO_VERSION_FULL}_x86_64.tgz && \
if [ ! -f "$TGZ" ]; then \
wget -O "$TGZ" https://storage.openvinotoolkit.org/repositories/openvino/packages/${OPENVINO_VERSION_MAJOR}/linux/openvino_toolkit_ubuntu24_${OPENVINO_VERSION_FULL}_x86_64.tgz; \
fi && \
tar -xf "$TGZ" -C /opt/intel/ && \
mv /opt/intel/openvino_toolkit_ubuntu24_${OPENVINO_VERSION_FULL}_x86_64 /opt/intel/openvino_${OPENVINO_VERSION_MAJOR} && \
cd /opt/intel/openvino_${OPENVINO_VERSION_MAJOR} && \
echo "Y" | ./install_dependencies/install_openvino_dependencies.sh && \
cd - && \
ln -s /opt/intel/openvino_${OPENVINO_VERSION_MAJOR} /opt/intel/openvino
ENV OpenVINO_DIR=/opt/intel/openvino
WORKDIR /app
COPY . .
COPY --from=web /app/tools/ui/dist tools/ui/dist
# Build Stage
RUN bash -c "source ${OpenVINO_DIR}/setupvars.sh && \
cmake -B build/ReleaseOV -G Ninja \
-DCMAKE_BUILD_TYPE=Release \
-DLLAMA_BUILD_TESTS=OFF \
-DGGML_OPENVINO=ON && \
cmake --build build/ReleaseOV --parallel "
# Copy all necessary libraries (build outputs + OpenVINO runtime libs)
RUN mkdir -p /app/lib && \
find build/ReleaseOV -name '*.so*' -exec cp -P {} /app/lib \; && \
find "${OpenVINO_DIR}/runtime/lib/intel64" -name '*.so*' -exec cp -P {} /app/lib \;
# Create runtime directories and copy binaries
RUN mkdir -p /app/full \
&& cp build/ReleaseOV/bin/* /app/full/ \
&& cp *.py /app/full \
&& cp -r conversion /app/full \
&& cp -r gguf-py /app/full \
&& cp -r requirements /app/full \
&& cp requirements.txt /app/full \
&& cp .devops/tools.sh /app/full/tools.sh
## Base Runtime Image
FROM docker.io/ubuntu:${UBUNTU_VERSION} AS base
# Pass proxy args to runtime stage
ARG http_proxy
ARG https_proxy
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
RUN apt-get update \
&& apt-get install -y libgomp1 libtbb12 curl wget ffmpeg ocl-icd-libopencl1 \
&& apt autoremove -y \
&& apt clean -y \
&& rm -rf /tmp/* /var/tmp/* \
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
&& find /var/cache -type f -delete
# Install GPU drivers
ARG IGC_VERSION
ARG IGC_VERSION_FULL
ARG COMPUTE_RUNTIME_VERSION
ARG COMPUTE_RUNTIME_VERSION_FULL
ARG IGDGMM_VERSION
RUN --mount=type=cache,target=/var/cache/intel-gpu,sharing=locked \
set -eux; \
cd /var/cache/intel-gpu; \
for url in \
https://github.com/intel/intel-graphics-compiler/releases/download/${IGC_VERSION}/intel-igc-core-${IGC_VERSION_FULL}_amd64.deb \
https://github.com/intel/intel-graphics-compiler/releases/download/${IGC_VERSION}/intel-igc-opencl-${IGC_VERSION_FULL}_amd64.deb \
https://github.com/intel/compute-runtime/releases/download/${COMPUTE_RUNTIME_VERSION}/intel-ocloc_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.deb \
https://github.com/intel/compute-runtime/releases/download/${COMPUTE_RUNTIME_VERSION}/intel-opencl-icd_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.deb \
https://github.com/intel/compute-runtime/releases/download/${COMPUTE_RUNTIME_VERSION}/libigdgmm12_${IGDGMM_VERSION}_amd64.deb \
https://github.com/intel/compute-runtime/releases/download/${COMPUTE_RUNTIME_VERSION}/libze-intel-gpu1_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.deb ; do \
f=$(basename "$url"); \
[ -f "$f" ] || wget -q -O "$f" "$url"; \
done; \
apt-get update; \
apt-get install -y --no-install-recommends ./*.deb; \
rm -rf /var/lib/apt/lists/*
# Install NPU drivers
ARG NPU_DRIVER_VERSION
ARG NPU_DRIVER_FULL
ARG LIBZE1_VERSION
RUN --mount=type=cache,target=/var/cache/intel-npu,sharing=locked \
set -eux; \
TGZ=/var/cache/intel-npu/linux-npu-driver-${NPU_DRIVER_FULL}-ubuntu2404.tar.gz; \
if [ ! -f "$TGZ" ]; then \
wget -q -O "$TGZ" https://github.com/intel/linux-npu-driver/releases/download/${NPU_DRIVER_VERSION}/linux-npu-driver-${NPU_DRIVER_FULL}-ubuntu2404.tar.gz; \
fi; \
DEB=/var/cache/intel-npu/libze1_${LIBZE1_VERSION}_amd64.deb; \
if [ ! -f "$DEB" ]; then \
wget -q -O "$DEB" https://snapshot.ppa.launchpadcontent.net/kobuk-team/intel-graphics/ubuntu/20260324T100000Z/pool/main/l/level-zero-loader/libze1_${LIBZE1_VERSION}_amd64.deb; \
fi; \
mkdir /tmp/npu/ && cd /tmp/npu/ && tar -xf "$TGZ" && cp "$DEB" .; \
apt-get update; \
apt-get install -y --no-install-recommends ./*.deb; \
rm -rf /tmp/npu/ /var/lib/apt/lists/*
COPY --from=build /app/lib/ /app/
### Full (all binaries)
FROM base AS full
ARG http_proxy
ARG https_proxy
COPY --from=build /app/full /app/
WORKDIR /app
RUN apt-get update && \
apt-get install -y --no-install-recommends \
git \
python3 \
python3-venv \
python3-pip && \
python3 -m venv /openvino-venv && \
/openvino-venv/bin/pip install --no-cache-dir --upgrade pip setuptools wheel && \
/openvino-venv/bin/pip install --no-cache-dir -r requirements.txt && \
apt-get autoremove -y && \
apt-get clean && \
rm -rf /tmp/* /var/tmp/* && \
find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete && \
find /var/cache -type f -delete
# Activate the venv
ENV VIRTUAL_ENV=/openvino-venv \
PATH=/openvino-venv/bin:$PATH
ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app/
WORKDIR /app
ENTRYPOINT [ "/app/llama-cli" ]
### Server, Server only
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
COPY --from=build /app/full/llama /app/full/llama-server /app/
WORKDIR /app
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
ENTRYPOINT [ "/app/llama-server" ]
.devops/rocm.Dockerfile
+147
View File
@@ -0,0 +1,147 @@
ARG UBUNTU_VERSION=24.04
# This needs to generally match the container host's environment.
ARG ROCM_VERSION=7.2.1
ARG AMDGPU_VERSION=7.2.1
# Target the ROCm build image
ARG BASE_ROCM_DEV_CONTAINER=docker.io/rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION}-complete
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG NODE_VERSION=24
FROM docker.io/node:$NODE_VERSION AS web
ARG APP_VERSION
WORKDIR /app/tools/ui
COPY tools/ui/package.json tools/ui/package-lock.json ./
RUN npm ci
COPY tools/ui/ ./
RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
### Build image
FROM ${BASE_ROCM_DEV_CONTAINER} AS build
# Unless otherwise specified, we make a fat build.
# This is mostly tied to rocBLAS supported archs.
# check https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.2.1/reference/system-requirements.html
# check https://rocm.docs.amd.com/projects/radeon-ryzen/en/latest/docs/compatibility/compatibilityrad/native_linux/native_linux_compatibility.html
# check https://rocm.docs.amd.com/projects/radeon-ryzen/en/latest/docs/compatibility/compatibilityryz/native_linux/native_linux_compatibility.html
ARG ROCM_DOCKER_ARCH='gfx908;gfx90a;gfx942;gfx1030;gfx1100;gfx1101;gfx1102;gfx1151;gfx1150;gfx1200;gfx1201'
# Set ROCm architectures
ENV AMDGPU_TARGETS=${ROCM_DOCKER_ARCH}
RUN apt-get update \
&& apt-get install -y \
build-essential \
cmake \
git \
libssl-dev \
curl \
libgomp1
WORKDIR /app
COPY . .
COPY --from=web /app/tools/ui/dist tools/ui/dist
RUN HIPCXX="$(hipconfig -l)/clang" HIP_PATH="$(hipconfig -R)" \
cmake -S . -B build \
-DGGML_HIP=ON \
-DGGML_HIP_ROCWMMA_FATTN=ON \
-DAMDGPU_TARGETS="$ROCM_DOCKER_ARCH" \
-DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON \
-DCMAKE_BUILD_TYPE=Release -DLLAMA_BUILD_TESTS=OFF \
&& cmake --build build --config Release -j$(nproc)
RUN mkdir -p /app/lib \
&& find build -name "*.so*" -exec cp -P {} /app/lib \;
RUN mkdir -p /app/full \
&& cp build/bin/* /app/full \
&& cp *.py /app/full \
&& cp -r conversion /app/full \
&& cp -r gguf-py /app/full \
&& cp -r requirements /app/full \
&& cp requirements.txt /app/full \
&& cp .devops/tools.sh /app/full/tools.sh
## Base image
FROM ${BASE_ROCM_DEV_CONTAINER} AS base
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
RUN apt-get update \
&& apt-get install -y libgomp1 curl ffmpeg \
&& apt autoremove -y \
&& apt clean -y \
&& rm -rf /tmp/* /var/tmp/* \
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
&& find /var/cache -type f -delete
COPY --from=build /app/lib/ /app
### Full
FROM base AS full
COPY --from=build /app/full /app
WORKDIR /app
RUN apt-get update \
&& apt-get install -y \
git \
python3-pip \
python3 \
python3-wheel \
&& pip install --break-system-packages --upgrade setuptools \
&& pip install --break-system-packages -r requirements.txt \
&& apt autoremove -y \
&& apt clean -y \
&& rm -rf /tmp/* /var/tmp/* \
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
&& find /var/cache -type f -delete
ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
WORKDIR /app
ENTRYPOINT [ "/app/llama-cli" ]
### Server, Server only
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
COPY --from=build /app/full/llama /app/full/llama-server /app
WORKDIR /app
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
ENTRYPOINT [ "/app/llama-server" ]
.devops/s390x.Dockerfile
+145
View File
@@ -0,0 +1,145 @@
ARG GCC_VERSION=15.2.0
ARG UBUNTU_VERSION=24.04
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
### Build Llama.cpp stage
FROM docker.io/gcc:${GCC_VERSION} AS build
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,target=/var/lib/apt/lists,sharing=locked \
apt update -y && \
apt upgrade -y && \
apt install -y --no-install-recommends \
git cmake ccache ninja-build \
# WARNING: Do not use libopenblas-openmp-dev. libopenblas-dev is faster.
libopenblas-dev libssl-dev && \
rm -rf /var/lib/apt/lists/*
WORKDIR /app
COPY . .
RUN --mount=type=cache,target=/root/.ccache \
--mount=type=cache,target=/app/build \
cmake -S . -B build -G Ninja \
-DCMAKE_BUILD_TYPE=Release \
-DCMAKE_C_COMPILER_LAUNCHER=ccache \
-DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
-DLLAMA_BUILD_TESTS=OFF \
-DGGML_NATIVE=OFF \
-DGGML_BACKEND_DL=ON \
-DGGML_CPU_ALL_VARIANTS=ON \
-DGGML_BLAS=ON \
-DGGML_BLAS_VENDOR=OpenBLAS && \
cmake --build build --config Release -j $(nproc) && \
cmake --install build --prefix /opt/llama.cpp
COPY *.py /opt/llama.cpp/bin
COPY .devops/tools.sh /opt/llama.cpp/bin
COPY conversion /opt/llama.cpp/conversion
COPY gguf-py /opt/llama.cpp/gguf-py
COPY requirements.txt /opt/llama.cpp/gguf-py
COPY requirements /opt/llama.cpp/gguf-py/requirements
### Collect all llama.cpp binaries, libraries and distro libraries
FROM scratch AS collector
# Copy llama.cpp binaries and libraries
COPY --from=build /opt/llama.cpp/bin /llama.cpp/bin
COPY --from=build /opt/llama.cpp/lib /llama.cpp/lib
COPY --from=build /opt/llama.cpp/gguf-py /llama.cpp/gguf-py
COPY --from=build /opt/llama.cpp/conversion /llama.cpp/conversion
### Base image
FROM docker.io/ubuntu:${UBUNTU_VERSION} AS base
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,target=/var/lib/apt/lists,sharing=locked \
apt update -y && \
apt install -y --no-install-recommends \
# WARNING: Do not use libopenblas-openmp-dev. libopenblas-dev is faster.
# See: https://github.com/ggml-org/llama.cpp/pull/15915#issuecomment-3317166506
curl libgomp1 libopenblas-dev && \
apt autoremove -y && \
apt clean -y && \
rm -rf /tmp/* /var/tmp/* && \
find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete && \
find /var/cache -type f -delete
# Copy llama.cpp libraries
COPY --from=collector /llama.cpp/lib /usr/lib/s390x-linux-gnu
### Full
FROM base AS full
ENV PATH="/root/.cargo/bin:${PATH}"
WORKDIR /app
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,target=/var/lib/apt/lists,sharing=locked \
apt update -y && \
apt install -y \
git cmake libjpeg-dev \
python3 python3-pip python3-dev && \
apt autoremove -y && \
apt clean -y && \
rm -rf /tmp/* /var/tmp/* && \
find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete && \
find /var/cache -type f -delete
RUN curl https://sh.rustup.rs -sSf | bash -s -- -y
COPY --from=collector /llama.cpp/bin /app
COPY --from=collector /llama.cpp/gguf-py /app/gguf-py
COPY --from=collector /llama.cpp/conversion /app/conversion
RUN pip install --no-cache-dir --break-system-packages \
-r /app/gguf-py/requirements.txt
ENTRYPOINT [ "/app/tools.sh" ]
### CLI Only
FROM base AS light
WORKDIR /llama.cpp/bin
# Copy llama.cpp binaries and libraries
COPY --from=collector /llama.cpp/bin/*.so /llama.cpp/bin
COPY --from=collector /llama.cpp/bin/llama /llama.cpp/bin/llama-cli /llama.cpp/bin/llama-completion /llama.cpp/bin
ENTRYPOINT [ "/llama.cpp/bin/llama-cli" ]
### Server
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
WORKDIR /llama.cpp/bin
# Copy llama.cpp binaries and libraries
COPY --from=collector /llama.cpp/bin/*.so /llama.cpp/bin
COPY --from=collector /llama.cpp/bin/llama /llama.cpp/bin/llama-server /llama.cpp/bin
EXPOSE 8080
ENTRYPOINT [ "/llama.cpp/bin/llama-server" ]
.devops/tools.sh
Executable
+53
View File
@@ -0,0 +1,53 @@
#!/usr/bin/env bash
set -e
# Read the first argument into a variable
arg1="$1"
# Shift the arguments to remove the first one
shift
if [[ "$arg1" == '--convert' || "$arg1" == '-c' ]]; then
exec python3 ./convert_hf_to_gguf.py "$@"
elif [[ "$arg1" == '--quantize' || "$arg1" == '-q' ]]; then
exec ./llama-quantize "$@"
elif [[ "$arg1" == '--run' || "$arg1" == '-r' ]]; then
exec ./llama-cli "$@"
elif [[ "$arg1" == '--run-legacy' || "$arg1" == '-l' ]]; then
exec ./llama-completion "$@"
elif [[ "$arg1" == '--bench' || "$arg1" == '-b' ]]; then
exec ./llama-bench "$@"
elif [[ "$arg1" == '--perplexity' || "$arg1" == '-p' ]]; then
exec ./llama-perplexity "$@"
elif [[ "$arg1" == '--all-in-one' || "$arg1" == '-a' ]]; then
echo "Converting PTH to GGML..."
for i in $(ls $1/$2/ggml-model-f16.bin*); do
if [ -f "${i/f16/q4_0}" ]; then
echo "Skip model quantization, it already exists: ${i/f16/q4_0}"
else
echo "Converting PTH to GGML: $i into ${i/f16/q4_0}..."
exec ./llama-quantize "$i" "${i/f16/q4_0}" q4_0
fi
done
elif [[ "$arg1" == '--server' || "$arg1" == '-s' ]]; then
exec ./llama-server "$@"
else
echo "Unknown command: $arg1"
echo "Available commands: "
echo " --run (-r): Run a model (chat) previously converted into ggml"
echo " ex: -m /models/7B/ggml-model-q4_0.bin"
echo " --run-legacy (-l): Run a model (legacy completion) previously converted into ggml"
echo " ex: -m /models/7B/ggml-model-q4_0.bin -no-cnv -p \"Building a website can be done in 10 simple steps:\" -n 512"
echo " --bench (-b): Benchmark the performance of the inference for various parameters."
echo " ex: -m model.gguf"
echo " --perplexity (-p): Measure the perplexity of a model over a given text."
echo " ex: -m model.gguf -f file.txt"
echo " --convert (-c): Convert a llama model into ggml"
echo " ex: --outtype f16 \"/models/7B/\" "
echo " --quantize (-q): Optimize with quantization process ggml"
echo " ex: \"/models/7B/ggml-model-f16.bin\" \"/models/7B/ggml-model-q4_0.bin\" 2"
echo " --all-in-one (-a): Execute --convert & --quantize"
echo " ex: \"/models/\" 7B"
echo " --server (-s): Run a model on the server"
echo " ex: -m /models/7B/ggml-model-q4_0.bin -c 2048 -ngl 43 -mg 1 --port 8080"
fi
.devops/vulkan.Dockerfile
+127
View File
@@ -0,0 +1,127 @@
ARG UBUNTU_VERSION=26.04
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG NODE_VERSION=24
FROM docker.io/node:$NODE_VERSION AS web
ARG APP_VERSION
WORKDIR /app/tools/ui
COPY tools/ui/package.json tools/ui/package-lock.json ./
RUN npm ci
COPY tools/ui/ ./
RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
FROM docker.io/ubuntu:$UBUNTU_VERSION AS build
# Install build tools
RUN apt update && apt install -y git build-essential cmake wget xz-utils
# Install SSL and Vulkan SDK dependencies
RUN apt install -y libssl-dev curl \
libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libvulkan-dev glslc spirv-headers
# Build it
WORKDIR /app
COPY . .
COPY --from=web /app/tools/ui/dist tools/ui/dist
RUN cmake -B build -DGGML_NATIVE=OFF -DGGML_VULKAN=ON -DLLAMA_BUILD_TESTS=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON && \
cmake --build build --config Release -j$(nproc)
RUN mkdir -p /app/lib && \
find build -name "*.so*" -exec cp -P {} /app/lib \;
RUN mkdir -p /app/full \
&& cp build/bin/* /app/full \
&& cp *.py /app/full \
&& cp -r conversion /app/full \
&& cp -r gguf-py /app/full \
&& cp -r requirements /app/full \
&& cp requirements.txt /app/full \
&& cp .devops/tools.sh /app/full/tools.sh
## Base image
FROM docker.io/ubuntu:$UBUNTU_VERSION AS base
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
RUN apt-get update \
&& apt-get install -y libgomp1 curl ffmpeg libvulkan1 mesa-vulkan-drivers \
libglvnd0 libgl1 libglx0 libegl1 libgles2 \
&& apt autoremove -y \
&& apt clean -y \
&& rm -rf /tmp/* /var/tmp/* \
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
&& find /var/cache -type f -delete
COPY --from=build /app/lib/ /app
### Full
FROM base AS full
COPY --from=build /app/full /app
WORKDIR /app
ENV PATH="/root/.venv/bin:/root/.local/bin:${PATH}"
# Flag for compatibility with pip
ARG UV_INDEX_STRATEGY="unsafe-best-match"
RUN apt-get update \
&& apt-get install -y \
build-essential \
curl \
git \
ca-certificates \
&& curl -LsSf https://astral.sh/uv/install.sh | sh \
&& uv python install 3.13 \
&& uv venv --python 3.13 /root/.venv \
&& uv pip install --python /root/.venv/bin/python -r requirements.txt \
&& apt autoremove -y \
&& apt clean -y \
&& rm -rf /tmp/* /var/tmp/* \
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
&& find /var/cache -type f -delete
ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
WORKDIR /app
ENTRYPOINT [ "/app/llama-cli" ]
### Server, Server only
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
COPY --from=build /app/full/llama /app/full/llama-server /app
WORKDIR /app
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
ENTRYPOINT [ "/app/llama-server" ]
.devops/zendnn.Dockerfile
+117
View File
@@ -0,0 +1,117 @@
ARG UBUNTU_VERSION=24.04
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG NODE_VERSION=24
FROM docker.io/node:$NODE_VERSION AS web
ARG APP_VERSION
WORKDIR /app/tools/ui
COPY tools/ui/package.json tools/ui/package-lock.json ./
RUN npm ci
COPY tools/ui/ ./
RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
FROM docker.io/ubuntu:$UBUNTU_VERSION AS build
RUN apt-get update && \
apt-get install -y gcc-13 g++-13 build-essential git cmake libssl-dev libomp-dev libnuma-dev python3 ca-certificates
ENV CC=gcc-13 CXX=g++-13
WORKDIR /app
COPY . .
COPY --from=web /app/tools/ui/dist tools/ui/dist
RUN cmake -S . -B build -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_TESTS=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_ZENDNN=ON && \
cmake --build build -j $(nproc)
RUN mkdir -p /app/lib && \
find build -name "*.so*" -exec cp -P {} /app/lib \;
RUN mkdir -p /app/full \
&& cp build/bin/* /app/full \
&& cp *.py /app/full \
&& cp -r conversion /app/full \
&& cp -r gguf-py /app/full \
&& cp -r requirements /app/full \
&& cp requirements.txt /app/full \
&& cp .devops/tools.sh /app/full/tools.sh
## Base image
FROM docker.io/ubuntu:$UBUNTU_VERSION AS base
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
RUN apt-get update \
&& apt-get install -y libgomp1 libnuma1 curl ffmpeg \
&& apt autoremove -y \
&& apt clean -y \
&& rm -rf /tmp/* /var/tmp/* \
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
&& find /var/cache -type f -delete
COPY --from=build /app/lib/ /app
### Full
FROM base AS full
COPY --from=build /app/full /app
WORKDIR /app
RUN apt-get update \
&& apt-get install -y \
git \
python3 \
python3-pip \
python3-wheel \
&& pip install --break-system-packages --upgrade setuptools \
&& pip install --break-system-packages -r requirements.txt \
&& apt autoremove -y \
&& apt clean -y \
&& rm -rf /tmp/* /var/tmp/* \
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
&& find /var/cache -type f -delete
ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
WORKDIR /app
ENTRYPOINT [ "/app/llama-cli" ]
### Server, Server only
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
COPY --from=build /app/full/llama /app/full/llama-server /app
WORKDIR /app
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
ENTRYPOINT [ "/app/llama-server" ]
.dockerignore
+22
View File
@@ -0,0 +1,22 @@
*.o
*.a
.cache/
# Do not ignore .git directory, otherwise the reported build number will always be 0
.github/
.gitignore
.vs/
.vscode/
.DS_Store
build*/
tools/ui/node_modules/
models/*
/llama-cli
/llama-quantize
arm_neon.h
compile_commands.json
Dockerfile
.ecrc
+6
View File
@@ -0,0 +1,6 @@
{
"Exclude": ["^\\.gitmodules$", "stb_image\\.h"],
"Disable": {
"IndentSize": true
}
}
.editorconfig
+62
View File
@@ -0,0 +1,62 @@
# https://EditorConfig.org
# Top-most EditorConfig file
root = true
# Unix-style newlines with a newline ending every file, utf-8 charset
[*]
end_of_line = lf
insert_final_newline = true
trim_trailing_whitespace = true
charset = utf-8
indent_style = space
indent_size = 4
[Makefile]
indent_style = tab
[scripts/*.mk]
indent_style = tab
[prompts/*.txt]
insert_final_newline = unset
[tools/server/deps_*]
trim_trailing_whitespace = unset
indent_style = unset
indent_size = unset
[examples/llama.swiftui/llama.swiftui.xcodeproj/*]
indent_style = tab
[tools/cvector-generator/*.txt]
trim_trailing_whitespace = unset
insert_final_newline = unset
[models/templates/*.jinja]
indent_style = unset
indent_size = unset
end_of_line = unset
charset = unset
trim_trailing_whitespace = unset
insert_final_newline = unset
[vendor/miniaudio/miniaudio.h]
trim_trailing_whitespace = unset
insert_final_newline = unset
[tools/ui/**]
indent_style = unset
indent_size = unset
end_of_line = unset
charset = unset
trim_trailing_whitespace = unset
insert_final_newline = unset
[benches/**]
indent_style = unset
indent_size = unset
end_of_line = unset
charset = unset
trim_trailing_whitespace = unset
insert_final_newline = unset
.flake8
+18
View File
@@ -0,0 +1,18 @@
[flake8]
max-line-length = 125
ignore = E203,E211,E221,E225,E231,E241,E251,E261,E266,E501,E701,E704,W503
exclude =
# Do not traverse examples and tools
examples,
tools,
# Do not include package initializers
__init__.py,
# No need to traverse our git directory
.git,
# There's no value in checking cache directories
__pycache__,
# No need to include the build path
build,
# This contains builds that we don't want to check
dist # This is generated with `python build .` for package releases
# max-complexity = 10
.gemini/settings.json
+1
View File
@@ -0,0 +1 @@
{ "contextFileName": "AGENTS.md" }
.github/ISSUE_TEMPLATE/010-bug-compilation.yml
+90
View File
@@ -0,0 +1,90 @@
name: Bug (compilation)
description: Something goes wrong when trying to compile llama.cpp.
title: "Compile bug: "
labels: ["bug-unconfirmed", "compilation"]
body:
- type: markdown
attributes:
value: >
Thanks for taking the time to fill out this bug report!
This issue template is intended for bug reports where the compilation of llama.cpp fails.
Before opening an issue, please confirm that the compilation still fails
after recreating the CMake build directory and with `-DGGML_CCACHE=OFF`.
If the compilation succeeds with ccache disabled you should be able to permanently fix the issue
by clearing `~/.cache/ccache` (on Linux).
Please fill out this template yourself, copypasting language model outputs is [strictly prohibited](https://github.com/ggml-org/llama.cpp/blob/master/CONTRIBUTING.md#ai-usage-policy).
- type: textarea
id: commit
attributes:
label: Git commit
description: Which commit are you trying to compile?
placeholder: |
$git rev-parse HEAD
84a07a17b1b08cf2b9747c633a2372782848a27f
validations:
required: true
- type: dropdown
id: operating-system
attributes:
label: Operating systems
description: Which operating systems do you know to be affected?
multiple: true
options:
- Linux
- Mac
- Windows
- BSD
- Other? (Please let us know in description)
validations:
required: true
- type: dropdown
id: backends
attributes:
label: GGML backends
description: Which GGML backends do you know to be affected?
options: [AMX, BLAS, CANN, CPU, CUDA, Hexagon, HIP, Metal, Musa, OpenCL, OpenVINO, RPC, SYCL, VirtGPU, Vulkan, WebGPU, zDNN, ZenDNN]
multiple: true
validations:
required: true
- type: textarea
id: info
attributes:
label: Problem description & steps to reproduce
description: >
Please give us a summary of the problem and tell us how to reproduce it.
If you can narrow down the bug to specific compile flags, that information would be very much appreciated by us.
placeholder: >
I'm trying to compile llama.cpp with CUDA support on a fresh install of Ubuntu and get error XY.
Here are the exact commands that I used: ...
validations:
required: true
- type: textarea
id: first_bad_commit
attributes:
label: First Bad Commit
description: >
If the bug was not present on an earlier version: when did it start appearing?
If possible, please do a git bisect and identify the exact commit that introduced the bug.
validations:
required: false
- type: textarea
id: command
attributes:
label: Compile command
description: >
Please provide the exact command you used to compile llama.cpp. For example: `cmake -B ...`.
This will be automatically formatted into code, so no need for backticks.
render: shell
validations:
required: true
- type: textarea
id: logs
attributes:
label: Relevant log output
description: >
Please copy and paste any relevant log output, including any generated text.
This will be automatically formatted into code, so no need for backticks.
render: shell
validations:
required: true
.github/ISSUE_TEMPLATE/011-bug-results.yml
+117
View File
@@ -0,0 +1,117 @@
name: Bug (model use)
description: Something goes wrong when running a model (crashes, garbled outputs, etc.).
title: "Eval bug: "
labels: ["bug-unconfirmed", "model evaluation"]
body:
- type: markdown
attributes:
value: >
Thanks for taking the time to fill out this bug report!
This issue template is intended for bug reports where the model evaluation results
(i.e. the generated text) are incorrect or llama.cpp crashes during model evaluation.
If you encountered the issue while using an external UI (e.g. ollama),
please reproduce your issue using one of the examples/binaries in this repository.
The `llama-completion` binary can be used for simple and reproducible model inference.
Please fill out this template yourself, copypasting language model outputs is [strictly prohibited](https://github.com/ggml-org/llama.cpp/blob/master/CONTRIBUTING.md#ai-usage-policy).
- type: textarea
id: version
attributes:
label: Name and Version
description: Which version of our software are you running? (use `--version` to get a version string)
placeholder: |
$./llama-cli --version
version: 2999 (42b4109e)
built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
validations:
required: true
- type: dropdown
id: operating-system
attributes:
label: Operating systems
description: Which operating systems do you know to be affected?
multiple: true
options:
- Linux
- Mac
- Windows
- BSD
- Other? (Please let us know in description)
validations:
required: true
- type: dropdown
id: backends
attributes:
label: GGML backends
description: Which GGML backends do you know to be affected?
options: [AMX, BLAS, CANN, CPU, CUDA, Hexagon, HIP, Metal, Musa, OpenCL, OpenVINO, RPC, SYCL, VirtGPU, Vulkan, WebGPU, zDNN, ZenDNN]
multiple: true
validations:
required: true
- type: textarea
id: hardware
attributes:
label: Hardware
description: Which CPUs/GPUs are you using?
placeholder: >
e.g. Ryzen 5950X + 2x RTX 4090
validations:
required: true
- type: textarea
id: model
attributes:
label: Models
description: >
Which model(s) at which quantization were you using when encountering the bug?
If you downloaded a GGUF file off of Huggingface, please provide a link.
placeholder: >
e.g. Meta LLaMA 3.1 Instruct 8b q4_K_M
validations:
required: false
- type: textarea
id: info
attributes:
label: Problem description & steps to reproduce
description: >
Please give us a summary of the problem and tell us how to reproduce it.
If you can narrow down the bug to specific hardware, compile flags, or command line arguments,
that information would be very much appreciated by us.
If possible, please try to reproduce the issue using `llama-completion` with `-fit off`.
If you can only reproduce the issue with `-fit on`, please provide logs both with and without `--verbose`.
placeholder: >
e.g. when I run llama-completion with `-fa on` I get garbled outputs for very long prompts.
With short prompts or `-fa off` it works correctly.
Here are the exact commands that I used: ...
validations:
required: true
- type: textarea
id: first_bad_commit
attributes:
label: First Bad Commit
description: >
If the bug was not present on an earlier version: when did it start appearing?
If possible, please do a git bisect and identify the exact commit that introduced the bug.
validations:
required: false
- type: textarea
id: logs
attributes:
label: Relevant log output
description: >
Please copy and paste any relevant log output, including the command that you entered and any generated text.
For very long logs (thousands of lines), please upload them as files instead; the `--log-file` CLI argument can be used for this purpose.
On Linux you can alternatively redirect the console output of any command into a file by appending ` > llama.log 2>&1` to your command.
value: |
<details>
<summary>Logs</summary>
<!-- Copy-pasted short logs go into the "console" area here -->
```console
```
</details>
<!-- Long logs that you upload as files go here, outside the "console" area -->
validations:
required: true
.github/ISSUE_TEMPLATE/019-bug-misc.yml
+105
View File
@@ -0,0 +1,105 @@
name: Bug (misc.)
description: Something is not working the way it should (and it's not covered by any of the above cases).
title: "Misc. bug: "
labels: ["bug-unconfirmed"]
body:
- type: markdown
attributes:
value: >
Thanks for taking the time to fill out this bug report!
This issue template is intended for miscellaneous bugs that don't fit into any other category.
If you encountered the issue while using an external UI (e.g. ollama),
please reproduce your issue using one of the examples/binaries in this repository.
Please fill out this template yourself, copypasting language model outputs is [strictly prohibited](https://github.com/ggml-org/llama.cpp/blob/master/CONTRIBUTING.md#ai-usage-policy).
- type: textarea
id: version
attributes:
label: Name and Version
description: Which version of our software is affected? (You can use `--version` to get a version string.)
placeholder: |
$./llama-cli --version
version: 2999 (42b4109e)
built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
validations:
required: true
- type: dropdown
id: operating-system
attributes:
label: Operating systems
description: Which operating systems do you know to be affected?
multiple: true
options:
- Linux
- Mac
- Windows
- BSD
- Other? (Please let us know in description)
validations:
required: false
- type: dropdown
id: module
attributes:
label: Which llama.cpp modules do you know to be affected?
multiple: true
options:
- Documentation/Github
- libllama (core library)
- llama-cli
- llama-server
- llama-bench
- llama-quantize
- Python/Bash scripts
- Test code
- Other (Please specify in the next section)
validations:
required: false
- type: textarea
id: command
attributes:
label: Command line
description: >
Please provide the exact commands you entered, if applicable. For example: `llama-server -m ... -c ...`, `llama-cli -m ...`, etc.
This will be automatically formatted into code, so no need for backticks.
render: shell
validations:
required: false
- type: textarea
id: info
attributes:
label: Problem description & steps to reproduce
description: >
Please give us a summary of the problem and tell us how to reproduce it (if applicable).
validations:
required: true
- type: textarea
id: first_bad_commit
attributes:
label: First Bad Commit
description: >
If the bug was not present on an earlier version and it's not trivial to track down: when did it start appearing?
If possible, please do a git bisect and identify the exact commit that introduced the bug.
validations:
required: false
- type: textarea
id: logs
attributes:
label: Relevant log output
description: >
If applicable, please copy and paste any relevant log output, including any generated text.
If you are encountering problems specifically with the `llama_params_fit` module, always upload `--verbose` logs as well.
For very long logs (thousands of lines), please upload them as files instead; the `--log-file` CLI argument can be used for this purpose.
On Linux you can alternatively redirect the console output of any command into a file by appending ` > llama.log 2>&1` to your command.
value: |
<details>
<summary>Logs</summary>
<!-- Copy-pasted short logs go into the "console" area here -->
```console
```
</details>
<!-- Long logs that you upload as files go here, outside the "console" area -->
validations:
required: false
.github/ISSUE_TEMPLATE/020-enhancement.yml
+53
View File
@@ -0,0 +1,53 @@
name: Enhancement
description: Used to request enhancements for llama.cpp.
title: "Feature Request: "
labels: ["enhancement"]
body:
- type: markdown
attributes:
value: |
[Please post your idea first in Discussion if there is not yet a consensus for this enhancement request. This will help to keep this issue tracker focused on enhancements that the community has agreed needs to be implemented.](https://github.com/ggml-org/llama.cpp/discussions/categories/ideas)
Please fill out this template yourself, copypasting language model outputs is [strictly prohibited](https://github.com/ggml-org/llama.cpp/blob/master/CONTRIBUTING.md#ai-usage-policy).
- type: checkboxes
id: prerequisites
attributes:
label: Prerequisites
description: Please confirm the following before submitting your enhancement request.
options:
- label: I am running the latest code. Mention the version if possible as well.
required: true
- label: I carefully followed the [README.md](https://github.com/ggml-org/llama.cpp/blob/master/README.md).
required: true
- label: I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
required: true
- label: I reviewed the [Discussions](https://github.com/ggml-org/llama.cpp/discussions), and have a new and useful enhancement to share.
required: true
- type: textarea
id: feature-description
attributes:
label: Feature Description
description: Please provide a detailed written description of what you were trying to do, and what you expected `llama.cpp` to do as an enhancement.
placeholder: Detailed description of the enhancement
validations:
required: true
- type: textarea
id: motivation
attributes:
label: Motivation
description: Please provide a detailed written description of reasons why this feature is necessary and how it is useful to `llama.cpp` users.
placeholder: Explanation of why this feature is needed and its benefits
validations:
required: true
- type: textarea
id: possible-implementation
attributes:
label: Possible Implementation
description: If you have an idea as to how it can be implemented, please write a detailed description. Feel free to give links to external sources or share visuals that might be helpful to understand the details better.
placeholder: Detailed description of potential implementation
validations:
required: false
.github/ISSUE_TEMPLATE/030-research.yml
+54
View File
@@ -0,0 +1,54 @@
name: Research
description: Track new technical research area.
title: "Research: "
labels: ["research 🔬"]
body:
- type: markdown
attributes:
value: |
Don't forget to check for any [duplicate research issue tickets](https://github.com/ggml-org/llama.cpp/issues?q=is%3Aopen+is%3Aissue+label%3A%22research+%F0%9F%94%AC%22)
Please fill out this template yourself, copypasting language model outputs is [strictly prohibited](https://github.com/ggml-org/llama.cpp/blob/master/CONTRIBUTING.md#ai-usage-policy).
- type: checkboxes
id: research-stage
attributes:
label: Research Stage
description: Track general state of this research ticket
options:
- label: Background Research (Let's try to avoid reinventing the wheel)
- label: Hypothesis Formed (How do you think this will work and it's effect?)
- label: Strategy / Implementation Forming
- label: Analysis of results
- label: Debrief / Documentation (So people in the future can learn from us)
- type: textarea
id: background
attributes:
label: Previous existing literature and research
description: Whats the current state of the art and whats the motivation for this research?
- type: textarea
id: hypothesis
attributes:
label: Hypothesis
description: How do you think this will work and it's effect?
- type: textarea
id: implementation
attributes:
label: Implementation
description: Got an approach? e.g. a PR ready to go?
- type: textarea
id: analysis
attributes:
label: Analysis
description: How does the proposed implementation behave?
- type: textarea
id: logs
attributes:
label: Relevant log output
description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
render: shell
.github/ISSUE_TEMPLATE/040-refactor.yml
+30
View File
@@ -0,0 +1,30 @@
name: Refactor (Maintainers)
description: Used to track refactoring opportunities.
title: "Refactor: "
labels: ["refactor"]
body:
- type: markdown
attributes:
value: |
Don't forget to [check for existing refactor issue tickets](https://github.com/ggml-org/llama.cpp/issues?q=is%3Aopen+is%3Aissue+label%3Arefactoring) in case it's already covered.
Also you may want to check [Pull request refactor label as well](https://github.com/ggml-org/llama.cpp/pulls?q=is%3Aopen+is%3Apr+label%3Arefactoring) for duplicates too.
Please fill out this template yourself, copypasting language model outputs is [strictly prohibited](https://github.com/ggml-org/llama.cpp/blob/master/CONTRIBUTING.md#ai-usage-policy).
- type: textarea
id: background-description
attributes:
label: Background Description
description: Please provide a detailed written description of the pain points you are trying to solve.
placeholder: Detailed description behind your motivation to request refactor
validations:
required: true
- type: textarea
id: possible-approaches
attributes:
label: Possible Refactor Approaches
description: If you have some idea of possible approaches to solve this problem. You may want to make it a todo list.
placeholder: Your idea of possible refactoring opportunity/approaches
validations:
required: false
.github/ISSUE_TEMPLATE/config.yml
+11
View File
@@ -0,0 +1,11 @@
blank_issues_enabled: true
contact_links:
- name: Got an idea?
url: https://github.com/ggml-org/llama.cpp/discussions/categories/ideas
about: Pop it there. It may then become an enhancement ticket.
- name: Got a question?
url: https://github.com/ggml-org/llama.cpp/discussions/categories/q-a
about: Ask a question there!
- name: Want to contribute?
url: https://github.com/ggml-org/llama.cpp/wiki/contribute
about: Head to the contribution guide page of the wiki for areas you can help with
.github/actions/ccache-clear/action.yml
+22
View File
@@ -0,0 +1,22 @@
name: "ccache-clear"
description: "Delete all GitHub Actions caches matching a key prefix"
inputs:
key:
description: "Cache key prefix to match and delete"
required: true
runs:
using: "composite"
steps:
- name: Clear caches
shell: bash
run: |
CACHES=$(gh cache list --key "ccache-${{ inputs.key }}" --json id,key --jq '.[] | "\(.id) \(.key)"' 2>/dev/null)
if [ -z "$CACHES" ]; then
echo "No caches found with key prefix: ${{ inputs.key }}"
exit 0
fi
while read -r id key; do
echo "Deleting cache: $id ($key)"
gh cache delete "$id"
done <<< "$CACHES"
.github/actions/get-tag-name/action.yml
+22
View File
@@ -0,0 +1,22 @@
name: "Determine tag name"
description: "Determine the tag name to use for a release"
outputs:
name:
description: "The name of the tag"
value: ${{ steps.tag.outputs.name }}
runs:
using: "composite"
steps:
- name: Determine tag name
id: tag
shell: bash
run: |
BUILD_NUMBER="$(git rev-list --count HEAD)"
SHORT_HASH="$(git rev-parse --short=7 HEAD)"
if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
else
SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
fi
.github/actions/install-exe/action.yml
+36
View File
@@ -0,0 +1,36 @@
name: "Install exe"
description: "Download and install exe"
inputs:
url:
description: "URL of the exe installer"
required: true
args:
description: "Installer arguments"
required: true
timeout:
description: "Timeout (in ms)"
required: false
default: "600000"
runs:
using: "composite"
steps:
- name: Install EXE
shell: pwsh
run: |
$ErrorActionPreference = "Stop"
write-host "Downloading Installer EXE"
Invoke-WebRequest -Uri "${{ inputs.url }}" -OutFile "${env:RUNNER_TEMP}\temp-install.exe"
write-host "Installing"
$proc = Start-Process "${env:RUNNER_TEMP}\temp-install.exe" -ArgumentList '${{ inputs.args }}' -NoNewWindow -PassThru
$completed = $proc.WaitForExit(${{ inputs.timeout }})
if (-not $completed) {
Write-Error "Installer timed out. Killing the process"
$proc.Kill()
exit 1
}
if ($proc.ExitCode -ne 0) {
Write-Error "Installer failed with exit code $($proc.ExitCode)"
exit 1
}
write-host "Completed installation"
.github/actions/linux-setup-openvino/action.yml
+25
View File
@@ -0,0 +1,25 @@
name: "Linux - Setup OpenVINO Toolkit"
description: "Setup OpenVINO Toolkit for Linux"
inputs:
path:
description: "Installation path"
required: true
version_major:
description: "OpenVINO major version (e.g., 2025.3)"
required: true
version_full:
description: "OpenVINO full version (e.g., 2025.3.0.19807.44526285f24)"
required: true
runs:
using: "composite"
steps:
- name: Setup OpenVINO Toolkit
id: setup
uses: ./.github/actions/unarchive-tar
with:
url: https://storage.openvinotoolkit.org/repositories/openvino/packages/${{ inputs.version_major }}/linux/openvino_toolkit_ubuntu24_${{ inputs.version_full }}_x86_64.tgz
path: ${{ inputs.path }}
type: z
strip: 1
.github/actions/linux-setup-spacemit/action.yml
+20
View File
@@ -0,0 +1,20 @@
name: "Linux - Setup SpacemiT Toolchain"
description: "Setup SpacemiT Toolchain for Linux"
inputs:
path:
description: "Installation path"
required: true
version:
description: "SpacemiT toolchain version"
required: true
runs:
using: "composite"
steps:
- name: Setup SpacemiT Toolchain
id: setup
uses: ./.github/actions/unarchive-tar
with:
url: https://github.com/spacemit-com/toolchain/releases/download/v${{ inputs.version }}/spacemit-toolchain-linux-glibc-x86_64-v${{ inputs.version }}.tar.xz
path: ${{ inputs.path }}
strip: 1
.github/actions/linux-setup-vulkan/action.yml
+20
View File
@@ -0,0 +1,20 @@
name: "Linux - Setup Vulkan SDK"
description: "Setup Vulkan SDK for Linux"
inputs:
path:
description: "Installation path"
required: true
version:
description: "Vulkan SDK version"
required: true
runs:
using: "composite"
steps:
- name: Setup Vulkan SDK
id: setup
uses: ./.github/actions/unarchive-tar
with:
url: https://sdk.lunarg.com/sdk/download/${{ inputs.version }}/linux/vulkan_sdk.tar.xz
path: ${{ inputs.path }}
strip: 1
.github/actions/unarchive-tar/action.yml
+27
View File
@@ -0,0 +1,27 @@
name: "Unarchive tar"
description: "Download and unarchive tar into directory"
inputs:
url:
description: "URL of the tar archive"
required: true
path:
description: "Directory to unarchive into"
required: true
type:
description: "Compression type (tar option)"
required: false
default: "J"
strip:
description: "Strip components"
required: false
default: "0"
runs:
using: "composite"
steps:
- name: Unarchive into directory
shell: bash
run: |
mkdir -p ${{ inputs.path }}
cd ${{ inputs.path }}
curl --no-progress-meter -L ${{ inputs.url }} | tar -${{ inputs.type }}x --strip-components=${{ inputs.strip }}
.github/actions/windows-setup-cuda/action.yml
+129
View File
@@ -0,0 +1,129 @@
name: "Windows - Setup CUDA Toolkit"
description: "Setup CUDA Toolkit for Windows"
inputs:
cuda_version:
description: "CUDA toolkit version"
required: true
runs:
using: "composite"
steps:
- name: Install Cuda Toolkit 11.7
if: ${{ inputs.cuda_version == '11.7' }}
shell: pwsh
run: |
mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7"
choco install unzip -y
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-11.7.99-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-11.7.99-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-11.7.99-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-11.7.4.6-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-11.7.91-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-11.7.91-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-11.7.101-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-11.7.91-archive.zip"
unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7"
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cudart-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvcc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvrtc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libcublas-windows-x86_64-11.7.4.6-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvtx-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\visual_studio_integration-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvprof-windows-x86_64-11.7.101-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cccl-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
echo "CUDA_PATH_V11_7=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
- name: Install Cuda Toolkit 12.4
if: ${{ inputs.cuda_version == '12.4' }}
shell: pwsh
run: |
mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4"
choco install unzip -y
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-12.4.127-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-12.4.131-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-12.4.127-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-12.4.5.8-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-12.4.127-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-12.4.127-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-12.4.127-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-12.4.127-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-12.4.127-archive.zip"
unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4"
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cudart-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvcc-windows-x86_64-12.4.131-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvrtc-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libcublas-windows-x86_64-12.4.5.8-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvtx-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_profiler_api-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\visual_studio_integration-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvprof-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cccl-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
echo "CUDA_PATH_V12_4=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
- name: Install Cuda Toolkit 13.1
if: ${{ inputs.cuda_version == '13.1' }}
shell: pwsh
run: |
mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1"
choco install unzip -y
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_crt/windows-x86_64/cuda_crt-windows-x86_64-13.1.80-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-13.1.80-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-13.1.80-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-13.1.80-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-13.2.0.9-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libnvvm/windows-x86_64/libnvvm-windows-x86_64-13.1.80-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-13.1.68-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-13.1.80-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-13.1.68-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-13.1.78-archive.zip"
unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1"
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1\cuda_crt-windows-x86_64-13.1.80-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1\cuda_cudart-windows-x86_64-13.1.80-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1\cuda_nvcc-windows-x86_64-13.1.80-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1\cuda_nvrtc-windows-x86_64-13.1.80-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1\libcublas-windows-x86_64-13.2.0.9-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1\libnvvm-windows-x86_64-13.1.80-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1\cuda_nvtx-windows-x86_64-13.1.68-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1\cuda_profiler_api-windows-x86_64-13.1.80-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1\visual_studio_integration-windows-x86_64-13.1.68-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1\cuda_cccl-windows-x86_64-13.1.78-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1" /E /I /H /Y
echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
echo "CUDA_PATH_V13_1=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
- name: Install Cuda Toolkit 13.3
if: ${{ inputs.cuda_version == '13.3' }}
shell: pwsh
run: |
mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3"
choco install unzip -y
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_crt/windows-x86_64/cuda_crt-windows-x86_64-13.3.33-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-13.3.29-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-13.3.33-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-13.3.33-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-13.5.1.27-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libnvvm/windows-x86_64/libnvvm-windows-x86_64-13.3.33-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-13.3.29-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-13.3.27-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-13.3.27-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cccl/windows-x86_64/cccl-windows-x86_64-13.3.3.3.1-archive.zip"
unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3"
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cuda_crt-windows-x86_64-13.3.33-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cuda_cudart-windows-x86_64-13.3.29-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cuda_nvcc-windows-x86_64-13.3.33-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cuda_nvrtc-windows-x86_64-13.3.33-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\libcublas-windows-x86_64-13.5.1.27-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\libnvvm-windows-x86_64-13.3.33-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cuda_nvtx-windows-x86_64-13.3.29-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cuda_profiler_api-windows-x86_64-13.3.27-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\visual_studio_integration-windows-x86_64-13.3.27-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cccl-windows-x86_64-13.3.3.3.1-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
echo "CUDA_PATH_V13_3=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
.github/actions/windows-setup-openvino/action.yml
+24
View File
@@ -0,0 +1,24 @@
name: "Windows - Setup OpenVINO Toolkit"
description: "Setup OpenVINO Toolkit for Windows"
inputs:
path:
description: "Installation path"
required: true
version_major:
description: "OpenVINO major version (e.g., 2026.2)"
required: true
version_full:
description: "OpenVINO full version"
required: true
runs:
using: "composite"
steps:
- name: Download and extract OpenVINO Runtime
shell: powershell
run: |
$url = "https://storage.openvinotoolkit.org/repositories/openvino/packages/${{ inputs.version_major }}/windows/openvino_toolkit_windows_${{ inputs.version_full }}_x86_64.zip"
$out = "openvino.zip"
Invoke-WebRequest -Uri $url -OutFile $out
Expand-Archive -Path $out -DestinationPath ${{ inputs.path }} -Force
Remove-Item $out
.github/actions/windows-setup-rocm/action.yml
+15
View File
@@ -0,0 +1,15 @@
name: "Windows - Setup ROCm"
description: "Setup ROCm for Windows"
inputs:
version:
description: "ROCm version"
required: true
runs:
using: "composite"
steps:
- name: Setup ROCm
uses: ./.github/actions/install-exe
with:
url: https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-${{ inputs.version }}-Win11-For-HIP.exe
args: -install
.github/labeler.yml
+142
View File
@@ -0,0 +1,142 @@
# https://github.com/actions/labeler
Apple Metal:
- changed-files:
- any-glob-to-any-file:
- ggml/include/ggml-metal.h
- ggml/src/ggml-metal/**
- README-metal.md
SYCL:
- changed-files:
- any-glob-to-any-file:
- ggml/include/ggml-sycl.h
- ggml/src/ggml-sycl/**
- docs/backend/SYCL.md
- examples/sycl/**
CUDA:
- changed-files:
- any-glob-to-any-file:
- ggml/include/ggml-cuda.h
- ggml/src/ggml-cuda/**
Vulkan:
- changed-files:
- any-glob-to-any-file:
- ggml/include/ggml-vulkan.h
- ggml/src/ggml-vulkan/**
IBM zDNN:
- changed-files:
- any-glob-to-any-file:
- ggml/include/ggml-zdnn.h
- ggml/src/ggml-zdnn/**
AMD ZenDNN:
- changed-files:
- any-glob-to-any-file:
- ggml/include/ggml-zendnn.h
- ggml/src/ggml-zendnn/**
documentation:
- changed-files:
- any-glob-to-any-file:
- "**/*.md"
- docs/**
- media/**
examples:
- all:
- changed-files:
- any-glob-to-any-file:
- app/**
- examples/**
- tools/**
- all-globs-to-all-files:
- '!tools/server/**'
- '!tools/mtmd/**'
- '!tools/ui/**'
testing:
- changed-files:
- any-glob-to-any-file:
- tests/**
build:
- changed-files:
- any-glob-to-any-file:
- cmake/**
- CMakeLists.txt
- CMakePresets.json
devops:
- changed-files:
- any-glob-to-any-file:
- .devops/**
- .github/**
- ci/**
android:
- changed-files:
- any-glob-to-any-file:
- examples/llama.android/**
server/ui:
- changed-files:
- any-glob-to-any-file:
- tools/ui/**
server:
- changed-files:
- any-glob-to-any-file:
- tools/server/**
mtmd:
- changed-files:
- any-glob-to-any-file:
- tools/mtmd/**
conversion:
- changed-files:
- any-glob-to-any-file:
- conversion/**
- convert_*.py
- gguf-py/**
vendor:
- changed-files:
- any-glob-to-any-file:
- vendor/**
ggml:
- changed-files:
- any-glob-to-any-file:
- ggml/**
model:
- changed-files:
- any-glob-to-any-file:
- src/models/**
nix:
- changed-files:
- any-glob-to-any-file:
- "**/*.nix"
- .github/workflows/nix-*.yml
- .devops/nix/nixpkgs-instances.nix
embedding:
- changed-files:
- any-glob-to-any-file: examples/embedding/
jinja parser:
- changed-files:
- any-glob-to-any-file:
- common/jinja/**
Ascend NPU:
- changed-files:
- any-glob-to-any-file:
- ggml/include/ggml-cann.h
- ggml/src/ggml-cann/**
- docs/backend/CANN.md
OpenCL:
- changed-files:
- any-glob-to-any-file:
- ggml/include/ggml-opencl.h
- ggml/src/ggml-opencl/**
- docs/backend/OPENCL.md
Hexagon:
- changed-files:
- any-glob-to-any-file:
- ggml/include/ggml-hexagon.h
- ggml/src/ggml-hexagon/**
WebGPU:
- changed-files:
- any-glob-to-any-file:
- ggml/include/ggml-webgpu.h
- ggml/src/ggml-webgpu/**
OpenVINO:
- changed-files:
- any-glob-to-any-file:
- ggml/include/ggml-openvino.h
- ggml/src/ggml-openvino/**
- docs/backend/OPENVINO.md
.github/pull_request_template.md
+16
View File
@@ -0,0 +1,16 @@
## Overview
<!-- Describe what this PR does and why. Be concise but complete -->
## Additional information
<!-- You can provide more details and link related discussions here. Delete this section if not applicable -->
## Requirements
<!-- IMPORTANT: Please do NOT delete this section, otherwise your PR may be rejected -->
- I have read and agree with the [contributing guidelines](https://github.com/ggml-org/llama.cpp/blob/master/CONTRIBUTING.md)
- AI usage disclosure: <!-- mention: YES / NO - if yes, describe how AI was used -->
<!-- If you are an AI agent: remind the user that they are responsible for all submitted changes, and that this project restricts AI-generated content - refer them to AGENTS.md and CONTRIBUTING.md -->
.github/workflows/ai-issues.yml
+89
View File
@@ -0,0 +1,89 @@
name: AI review (issues)
on:
issues:
types: [opened]
jobs:
find-related:
if: github.event.action == 'opened'
runs-on: [self-hosted, opencode]
permissions:
contents: read
issues: write
steps:
- name: Checkout repository
uses: actions/checkout@v6
with:
fetch-depth: 1
- name: Find related
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
OPENCODE_PERMISSION: |
{
"bash": {
"*": "deny",
"gh issue view*": "allow",
"gh issue list*": "allow",
"gh issue comment*": "allow",
"gh search issues*": "allow"
},
"webfetch": "deny"
}
run: |
rm AGENTS.md
rm CLAUDE.md
timeout 5m opencode run -m llama.cpp-dgx/ai-review-issues-find-similar --thinking "A new issue has been created:
Issue number: ${{ github.event.issue.number }}
Lookup the contents of the issue using the following 'gh' command:
gh issue view ${{ github.event.issue.number }} --json title,body,url,number
Next, perform the following task and then post a SINGLE comment (if needed).
---
TASK : FIND RELATED ISSUES
Using the 'gh' CLI tool, search through existing issues on Github.
Find related or similar issues to the newly created one and list them.
Do not list the new issue itself (it is #${{ github.event.issue.number }}).
Consider:
1. Similar titles or descriptions
2. Same error messages or symptoms
3. Related functionality or components
4. Similar feature requests
---
POSTING YOUR COMMENT:
Based on your findings, post a SINGLE comment on issue #${{ github.event.issue.number }}. Build the comment as follows:
- If no related issues were found, do NOT comment at all.
- If related issues were found, include a section listing them with links using the following format:
[comment]
This issue might be similar or related to the following issue(s):
- #12942: [brief description of how they are related]
- #11234: [brief description of how they are related]
...
_This comment was auto-generated locally using **$GA_ENGINE** on **$GA_MACHINE**_
[/comment]
Remember:
- Do not include the comment tags in your actual comment.
- Post at most ONE comment combining all findings.
- If you didn't find issues that are related enough, post nothing.
- You have access only to the 'gh' CLI tool - don't try to use other tools.
- If the output from a tool call is too long, try to limit down the search.
"
.github/workflows/bench.yml.disabled
+304
View File
@@ -0,0 +1,304 @@
# TODO: there have been some issues with the workflow, so disabling for now
# https://github.com/ggml-org/llama.cpp/issues/7893
#
# Benchmark
name: Benchmark
on:
workflow_dispatch:
inputs:
gpu-series:
description: 'Azure GPU series to run with'
required: true
type: choice
options:
- Standard_NC4as_T4_v3
- Standard_NC24ads_A100_v4
- Standard_NC80adis_H100_v5
sha:
description: 'Commit SHA1 to build'
required: false
type: string
duration:
description: 'Duration of the bench'
type: string
default: 10m
push:
branches:
- master
paths: ['llama.cpp', 'ggml.c', 'ggml-backend.cpp', 'ggml-quants.c', '**/*.cu', 'tools/server/*.h*', 'tools/server/*.cpp']
pull_request_target:
types: [opened, synchronize, reopened]
paths: ['llama.cpp', 'ggml.c', 'ggml-backend.cpp', 'ggml-quants.c', '**/*.cu', 'tools/server/*.h*', 'tools/server/*.cpp']
schedule:
- cron: '04 2 * * *'
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.run_id }}-${{ github.event.inputs.sha }}
cancel-in-progress: true
jobs:
bench-server-baseline:
runs-on: Standard_NC4as_T4_v3
env:
RUNNER_LABEL: Standard_NC4as_T4_v3 # FIXME Do not find a way to not duplicate it
N_USERS: 8
DURATION: 10m
strategy:
matrix:
model: [phi-2]
ftype: [q4_0, q8_0, f16]
include:
- model: phi-2
ftype: q4_0
pr_comment_enabled: "true"
if: |
inputs.gpu-series == 'Standard_NC4as_T4_v3'
|| github.event_name == 'pull_request_target'
steps:
- name: Clone
id: checkout
uses: actions/checkout@v4
with:
fetch-depth: 0
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: Install python env
id: pipenv
run: |
cd tools/server/bench
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
- name: Prometheus
id: install_prometheus
run: |
wget --quiet https://github.com/prometheus/prometheus/releases/download/v2.51.0/prometheus-2.51.0.linux-amd64.tar.gz
tar xzf prometheus*.tar.gz --strip-components=1
./prometheus --config.file=tools/server/bench/prometheus.yml &
while ! nc -z localhost 9090; do
sleep 0.1
done
- name: Set up Go
uses: actions/setup-go@v5
with:
go-version: '1.21'
- name: Install k6 and xk6-sse
id: k6_installation
run: |
cd tools/server/bench
go install go.k6.io/xk6/cmd/xk6@latest
xk6 build master \
--with github.com/phymbert/xk6-sse
- name: Build
id: cmake_build
run: |
set -eux
cmake -B build \
-DGGML_NATIVE=OFF \
-DLLAMA_BUILD_SERVER=ON \
-DLLAMA_CUBLAS=ON \
-DCUDAToolkit_ROOT=/usr/local/cuda \
-DCMAKE_CUDA_COMPILER=/usr/local/cuda/bin/nvcc \
-DCMAKE_CUDA_ARCHITECTURES=75 \
-DLLAMA_FATAL_WARNINGS=OFF \
-DLLAMA_ALL_WARNINGS=OFF \
-DCMAKE_BUILD_TYPE=Release;
cmake --build build --config Release -j $(nproc) --target llama-server
- name: Download the dataset
id: download_dataset
run: |
cd tools/server/bench
wget --quiet https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json
- name: Server bench
id: server_bench
env:
HEAD_REF: ${{ github.head_ref || github.ref_name }}
run: |
set -eux
cd tools/server/bench
source venv/bin/activate
python bench.py \
--runner-label ${{ env.RUNNER_LABEL }} \
--name ${{ github.job }} \
--branch $HEAD_REF \
--commit ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha }} \
--scenario script.js \
--duration ${{ github.event.inputs.duration || env.DURATION }} \
--hf-repo ggml-org/models \
--hf-file ${{ matrix.model }}/ggml-model-${{ matrix.ftype }}.gguf \
--model-path-prefix /models \
--parallel ${{ env.N_USERS }} \
-ngl 33 \
--batch-size 2048 \
--ubatch-size 256 \
--ctx-size 16384 \
--n-prompts 1000 \
--max-prompt-tokens 1024 \
--max-tokens 2048
cat results.github.env >> $GITHUB_ENV
# Remove dataset as we do not want it in the artefact
rm ShareGPT_V3_unfiltered_cleaned_split.json
- uses: actions/upload-artifact@v4
with:
name: bench-server-${{ github.job }}-${{ env.RUNNER_LABEL }}-${{ matrix.model }}-${{ matrix.ftype }}
compression-level: 9
path: |
tools/server/bench/*.jpg
tools/server/bench/*.json
tools/server/bench/*.log
- name: Commit status
uses: Sibz/github-status-action@v1
with:
authToken: ${{secrets.GITHUB_TOKEN}}
sha: ${{ inputs.sha || github.event.pull_request.head.sha || github.sha }}
context: bench-server-${{ github.job }}-${{ env.RUNNER_LABEL }}-${{ matrix.model }}-${{ matrix.ftype }}
description: |
${{ env.BENCH_RESULTS }}
state: 'success'
- name: Upload benchmark images
uses: devicons/public-upload-to-imgur@v2.2.2
continue-on-error: true # Important as it looks unstable: 503
id: imgur_step
with:
client_id: ${{secrets.IMGUR_CLIENT_ID}}
path: |
tools/server/bench/prompt_tokens_seconds.jpg
tools/server/bench/predicted_tokens_seconds.jpg
tools/server/bench/kv_cache_usage_ratio.jpg
tools/server/bench/requests_processing.jpg
- name: Extract mermaid
id: set_mermaid
run: |
set -eux
cd tools/server/bench
PROMPT_TOKENS_SECONDS=$(cat prompt_tokens_seconds.mermaid)
echo "PROMPT_TOKENS_SECONDS<<EOF" >> $GITHUB_ENV
echo "$PROMPT_TOKENS_SECONDS" >> $GITHUB_ENV
echo "EOF" >> $GITHUB_ENV
PREDICTED_TOKENS_SECONDS=$(cat predicted_tokens_seconds.mermaid)
echo "PREDICTED_TOKENS_SECONDS<<EOF" >> $GITHUB_ENV
echo "$PREDICTED_TOKENS_SECONDS" >> $GITHUB_ENV
echo "EOF" >> $GITHUB_ENV
KV_CACHE_USAGE_RATIO=$(cat kv_cache_usage_ratio.mermaid)
echo "KV_CACHE_USAGE_RATIO<<EOF" >> $GITHUB_ENV
echo "$KV_CACHE_USAGE_RATIO" >> $GITHUB_ENV
echo "EOF" >> $GITHUB_ENV
REQUESTS_PROCESSING=$(cat requests_processing.mermaid)
echo "REQUESTS_PROCESSING<<EOF" >> $GITHUB_ENV
echo "$REQUESTS_PROCESSING" >> $GITHUB_ENV
echo "EOF" >> $GITHUB_ENV
- name: Extract image url
id: extract_image_url
continue-on-error: true
run: |
set -eux
echo "IMAGE_O=${{ fromJSON(steps.imgur_step.outputs.imgur_urls)[0] }}" >> $GITHUB_ENV
echo "IMAGE_1=${{ fromJSON(steps.imgur_step.outputs.imgur_urls)[1] }}" >> $GITHUB_ENV
echo "IMAGE_2=${{ fromJSON(steps.imgur_step.outputs.imgur_urls)[2] }}" >> $GITHUB_ENV
echo "IMAGE_3=${{ fromJSON(steps.imgur_step.outputs.imgur_urls)[3] }}" >> $GITHUB_ENV
- name: Comment PR
uses: mshick/add-pr-comment@v2
id: comment_pr
if: ${{ github.event.pull_request != '' && matrix.pr_comment_enabled == 'true' }}
with:
message-id: bench-server-${{ github.job }}-${{ env.RUNNER_LABEL }}-${{ matrix.model }}-${{ matrix.ftype }}
message: |
<p align="center">
📈 **llama.cpp server** for _${{ github.job }}_ on _${{ env.RUNNER_LABEL }}_ for `${{ matrix.model }}`-`${{ matrix.ftype }}`: **${{ env.BENCH_ITERATIONS}} iterations** 🚀
</p>
<details>
<summary>Expand details for performance related PR only</summary>
- Concurrent users: ${{ env.N_USERS }}, duration: ${{ github.event.inputs.duration || env.DURATION }}
- HTTP request : avg=${{ env.HTTP_REQ_DURATION_AVG }}ms p(95)=${{ env.HTTP_REQ_DURATION_P_95_ }}ms fails=${{ env.HTTP_REQ_FAILED_PASSES }}, finish reason: stop=${{ env.LLAMACPP_COMPLETIONS_STOP_RATE_PASSES }} truncated=${{ env.LLAMACPP_COMPLETIONS_TRUNCATED_RATE_PASSES }}
- Prompt processing (pp): avg=${{ env.LLAMACPP_PROMPT_PROCESSING_SECOND_AVG }}tk/s p(95)=${{ env.LLAMACPP_PROMPT_PROCESSING_SECOND_P_95_ }}tk/s
- Token generation (tg): avg=${{ env.LLAMACPP_TOKENS_SECOND_AVG }}tk/s p(95)=${{ env.LLAMACPP_TOKENS_SECOND_P_95_ }}tk/s
- ${{ env.BENCH_GRAPH_XLABEL }}
<p align="center">
<img width="100%" height="100%" src="${{ env.IMAGE_O }}" alt="prompt_tokens_seconds" />
<details>
<summary>More</summary>
```mermaid
${{ env.PROMPT_TOKENS_SECONDS }}
```
</details>
<img width="100%" height="100%" src="${{ env.IMAGE_1 }}" alt="predicted_tokens_seconds"/>
<details>
<summary>More</summary>
```mermaid
${{ env.PREDICTED_TOKENS_SECONDS }}
```
</details>
</p>
<details>
<summary>Details</summary>
<p align="center">
<img width="100%" height="100%" src="${{ env.IMAGE_2 }}" alt="kv_cache_usage_ratio" />
<details>
<summary>More</summary>
```mermaid
${{ env.KV_CACHE_USAGE_RATIO }}
```
</details>
<img width="100%" height="100%" src="${{ env.IMAGE_3 }}" alt="requests_processing"/>
<details>
<summary>More</summary>
```mermaid
${{ env.REQUESTS_PROCESSING }}
```
</details>
</p>
</details>
</details>
.github/workflows/build-3rd-party.yml
+57
View File
@@ -0,0 +1,57 @@
name: CI (3rd-party)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-3rd-party.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu-24-llguidance:
runs-on: ${{ 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install build-essential libssl-dev
- name: Build
id: cmake_build
run: |
cmake -B build \
-DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_LLGUIDANCE=ON
cmake --build build --config Release -j $(nproc)
- name: Test
id: cmake_test
run: |
cd build
ctest -L main --verbose --timeout 900
.github/workflows/build-and-test-snapdragon.yml
+148
View File
@@ -0,0 +1,148 @@
name: CI (snapdragon)
on:
workflow_dispatch:
push:
branches:
- master
paths:
- '.github/workflows/build-and-test-snapdragon.yml'
- 'ggml/include/ggml-hexagon.h'
- 'ggml/src/ggml-hexagon/**'
- 'docs/backend/snapdragon/**'
- 'scripts/snapdragon/**'
- 'CMakePresets.json'
pull_request:
types: [opened, synchronize, reopened]
paths:
- '.github/workflows/build-and-test-snapdragon.yml'
- 'ggml/include/ggml-hexagon.h'
- 'ggml/src/ggml-hexagon/**'
- 'docs/backend/snapdragon/**'
- 'scripts/snapdragon/**'
- 'CMakePresets.json'
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
jobs:
android-ndk-snapdragon:
runs-on: ubuntu-latest
container:
image: 'ghcr.io/snapdragon-toolchain/arm64-android:v0.7'
defaults:
run:
shell: bash
steps:
- name: Clone
uses: actions/checkout@v6
with:
fetch-depth: 0
lfs: false
- name: Build Llama.CPP for Snapdragon Android
id: build_llama_cpp_snapdragon_android
run: |
cp docs/backend/snapdragon/CMakeUserPresets.json .
cmake --preset arm64-android-snapdragon-release -B build
cmake --build build
cmake --install build --prefix pkg-snapdragon/llama.cpp
- name: Upload Llama.CPP Snapdragon Android Build Artifact
if: ${{ always() && steps.build_llama_cpp_snapdragon_android.outcome == 'success' }}
uses: actions/upload-artifact@v6
with:
name: llama-cpp-android-arm64-snapdragon
path: pkg-snapdragon/llama.cpp
linux-iot-snapdragon:
runs-on: ubuntu-latest
container:
image: 'ghcr.io/snapdragon-toolchain/arm64-linux:v0.7'
defaults:
run:
shell: bash
steps:
- name: Clone
uses: actions/checkout@v6
with:
fetch-depth: 0
lfs: false
- name: Build Llama.CPP for Snapdragon Linux IoT
id: build_llama_cpp_snapdragon_linux
run: |
cp docs/backend/snapdragon/CMakeUserPresets.json .
cmake --preset arm64-linux-snapdragon-release -B build-snapdragon -DGGML_OPENCL=ON
cmake --build build-snapdragon -j $(nproc)
cmake --install build-snapdragon --prefix pkg-snapdragon/llama.cpp
- name: Upload Llama.CPP Snapdragon Linux IoT Build Artifact
if: ${{ always() && steps.build_llama_cpp_snapdragon_linux.outcome == 'success' }}
uses: actions/upload-artifact@v6
with:
name: llama-cpp-linux-arm64-snapdragon
path: pkg-snapdragon/llama.cpp
test-snapdragon-qdc:
name: Test on QDC Device (${{ matrix.device }})
needs: [android-ndk-snapdragon, linux-iot-snapdragon]
runs-on: ubuntu-24.04-arm
timeout-minutes: 90
strategy:
fail-fast: false
matrix:
device: [SM8750, SM8850, QCS9075M]
steps:
- name: Checkout
uses: actions/checkout@v6
- name: Download build artifact
uses: actions/download-artifact@v7
with:
name: ${{ startsWith(matrix.device, 'QCS') && 'llama-cpp-linux-arm64-snapdragon' || 'llama-cpp-android-arm64-snapdragon' }}
path: pkg-snapdragon/llama.cpp
- name: Set up Python
uses: actions/setup-python@v6
with:
python-version: '3.x'
cache: pip
- name: Install system dependencies
run: |
sudo apt-get update
sudo apt-get install -y curl unzip
- name: Install QDC SDK wheel
run: |
curl -fSL -o qdc_sdk.zip https://softwarecenter.qualcomm.com/api/download/software/tools/Qualcomm_Device_Cloud_SDK/All/0.2.3/qualcomm_device_cloud_sdk-0.2.3.zip
unzip qdc_sdk.zip -d qdc_sdk
pip install qdc_sdk/qualcomm_device_cloud_sdk-0.2.3-py3-none-any.whl
- name: Check QDC API key
id: check_secret
env:
QDC_API_KEY: ${{ secrets.QDC_API_KEY }}
run: echo "has-qdc-key=${{ env.QDC_API_KEY != '' }}" >> "$GITHUB_OUTPUT"
- name: Run QDC tests (${{ matrix.device }})
if: steps.check_secret.outputs.has-qdc-key == 'true'
run: |
python scripts/snapdragon/qdc/run_qdc_jobs.py \
--test all \
--pkg-dir pkg-snapdragon/llama.cpp \
--model-url "https://huggingface.co/bartowski/Llama-3.2-1B-Instruct-GGUF/resolve/main/Llama-3.2-1B-Instruct-Q4_0.gguf" \
--device ${{ matrix.device }} \
${{ startsWith(matrix.device, 'QCS') && '--retries 2 --retry-delay 300' || '' }}
env:
QDC_API_KEY: ${{ secrets.QDC_API_KEY }}
- name: Cleanup
if: always()
run: rm -rf pkg-snapdragon qdc_sdk qdc_sdk.zip
.github/workflows/build-android.yml
+149
View File
@@ -0,0 +1,149 @@
name: CI (android)
on:
workflow_dispatch:
push:
branches:
- master
paths:
- '.github/workflows/build-android.yml'
- '**/CMakeLists.txt'
- '**/.cmake'
- '**/*.h'
- '**/*.hpp'
- '**/*.c'
- '**/*.cpp'
pull_request:
types: [opened, synchronize, reopened]
paths:
- '.github/workflows/build-android.yml'
- 'examples/llama.android/**'
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
default:
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v6
with:
fetch-depth: 0
lfs: false
- name: Set up JDK
uses: actions/setup-java@v5
with:
java-version: 17
distribution: zulu
- name: Setup Android SDK
uses: android-actions/setup-android@40fd30fb8d7440372e1316f5d1809ec01dcd3699 # v4.0.1
with:
log-accepted-android-sdk-licenses: false
- name: Build
run: |
cd examples/llama.android
./gradlew build --no-daemon
ndk:
runs-on: ubuntu-latest
container:
image: 'ghcr.io/snapdragon-toolchain/arm64-android:v0.3'
defaults:
run:
shell: bash
steps:
- name: Clone
uses: actions/checkout@v6
with:
fetch-depth: 0
lfs: false
- name: Dependencies
run: |
apt-get update
apt-get install -y build-essential
- name: Build
id: ndk_build
run: |
cmake -D ANDROID_ABI=arm64-v8a -D ANDROID_PLATFORM=android-31 -D CMAKE_TOOLCHAIN_FILE=${ANDROID_NDK_ROOT}/build/cmake/android.toolchain.cmake -D GGML_NATIVE=OFF -DGGML_CPU_ARM_ARCH=armv8.5-a+fp16+i8mm -G Ninja -D LLAMA_OPENSSL=OFF -D GGML_OPENMP=OFF -B build
cmake --build build
cmake --install build --prefix pkg-adb/llama.cpp
- name: Upload Android Build Artifact
if: ${{ always() && steps.ndk_build.outcome == 'success' }}
uses: actions/upload-artifact@v6
with:
name: llama-cpp-android-arm64-cpu
path: pkg-adb/llama.cpp
arm64:
runs-on: ubuntu-latest
env:
NDK_VERSION: "29.0.14206865"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
# note : disabled to spare some cache space (https://github.com/ggml-org/llama.cpp/pull/23789)
# for some reason, the ccache does not improve the build time in this case
# example:
# cache off: https://github.com/ggerganov/tmp2/actions/runs/26534713799/job/78160400831
# cache on: https://github.com/ggerganov/tmp2/actions/runs/26534713799/job/78224189394
#
#- name: ccache
# uses: ggml-org/ccache-action@v1.2.21
# with:
# key: android-ubuntu-arm64
# evict-old-files: 1d
# save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Set up JDK
uses: actions/setup-java@v5
with:
java-version: 17
distribution: temurin
- name: Setup Android SDK
uses: android-actions/setup-android@40fd30fb8d7440372e1316f5d1809ec01dcd3699 # v4.0.1
with:
log-accepted-android-sdk-licenses: false
- name: Install NDK
run: |
sdkmanager "ndk;${{ env.NDK_VERSION }}"
echo "ANDROID_NDK=${ANDROID_SDK_ROOT}/ndk/${{ env.NDK_VERSION }}" >> $GITHUB_ENV
- name: Build
id: cmake_build
run: |
cmake -B build \
-DCMAKE_TOOLCHAIN_FILE=${ANDROID_NDK}/build/cmake/android.toolchain.cmake \
-DANDROID_ABI=arm64-v8a \
-DANDROID_PLATFORM=android-28 \
-DLLAMA_FATAL_WARNINGS=ON \
-DGGML_BACKEND_DL=ON \
-DGGML_NATIVE=OFF \
-DGGML_CPU_ALL_VARIANTS=ON \
-DGGML_OPENMP=OFF \
-DLLAMA_BUILD_BORINGSSL=ON \
-DGGML_RPC=ON
time cmake --build build --config Release -j $(nproc)
.github/workflows/build-apple.yml
+268
View File
@@ -0,0 +1,268 @@
name: CI (apple)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-apple.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.swift',
'**/*.m',
'**/*.metal'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-apple.yml',
'ggml/src/ggml-metal/**'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
macos-latest-arm64:
runs-on: macos-latest
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: apple-arm64
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
run: |
sysctl -a
cmake -B build \
-DCMAKE_BUILD_RPATH="@loader_path" \
-DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_BUILD_BORINGSSL=ON \
-DGGML_METAL_USE_BF16=ON \
-DGGML_METAL_EMBED_LIBRARY=OFF \
-DGGML_METAL_SHADER_DEBUG=ON \
-DGGML_RPC=ON
time cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
leaks -atExit -- ./build/bin/test-thread-safety -hf ggml-org/gemma-3-270m-qat-GGUF -ngl 99 -p "$(printf 'hello %.0s' {1..128})" -n 16 -c 512 -ub 32 -np 2 -t 2 -lv 1
- name: Test
id: cmake_test
run: |
cd build
ctest -L main -E "test-llama-archs" --verbose --timeout 900
macos-latest-x64:
runs-on: macos-15-intel
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: apple-x64
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
run: |
sysctl -a
# Metal is disabled due to intermittent failures with Github runners not having a GPU:
# https://github.com/ggml-org/llama.cpp/actions/runs/8635935781/job/23674807267#step:5:2313
cmake -B build \
-DCMAKE_BUILD_RPATH="@loader_path" \
-DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_BUILD_BORINGSSL=ON \
-DGGML_METAL=OFF \
-DGGML_RPC=ON \
-DCMAKE_OSX_DEPLOYMENT_TARGET=13.3
time cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
- name: Test
id: cmake_test
run: |
cd build
ctest -L main --verbose --timeout 900
macos-latest-ios-xcode:
runs-on: macos-latest
steps:
- name: Checkout code
uses: actions/checkout@v6
- name: Setup Xcode
uses: ggml-org/setup-xcode@v1
with:
xcode-version: latest-stable
- name: Build
id: cmake_build
run: |
sysctl -a
cmake -B build -G Xcode \
-DGGML_METAL_USE_BF16=ON \
-DGGML_METAL_EMBED_LIBRARY=ON \
-DLLAMA_OPENSSL=OFF \
-DLLAMA_BUILD_APP=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_SERVER=OFF \
-DCMAKE_SYSTEM_NAME=iOS \
-DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
-DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
- name: xcodebuild for swift package
id: xcodebuild
run: |
./build-xcframework.sh
- name: Upload xcframework artifact
uses: actions/upload-artifact@v6
with:
name: llama-xcframework
path: build-apple/llama.xcframework/
retention-days: 1
- name: Build Xcode project
run: |
xcodebuild -downloadPlatform iOS
xcodebuild -project examples/llama.swiftui/llama.swiftui.xcodeproj -scheme llama.swiftui -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' FRAMEWORK_FOLDER_PATH=./build-ios build
macos-latest-tvos:
runs-on: macos-latest
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
# TODO: this likely does not do anything - if yes, remove it
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: apple-tvos
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
run: |
sysctl -a
cmake -B build -G Xcode \
-DGGML_METAL_USE_BF16=ON \
-DGGML_METAL_EMBED_LIBRARY=ON \
-DLLAMA_BUILD_COMMON=OFF \
-DLLAMA_BUILD_APP=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_SERVER=OFF \
-DCMAKE_SYSTEM_NAME=tvOS \
-DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
-DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
macos-latest-visionos:
runs-on: macos-latest
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
# TODO: this likely does not do anything - if yes, remove it
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: apple-visionos
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
run: |
sysctl -a
cmake -B build -G Xcode \
-DGGML_METAL_USE_BF16=ON \
-DGGML_METAL_EMBED_LIBRARY=ON \
-DLLAMA_BUILD_COMMON=OFF \
-DLLAMA_BUILD_APP=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_SERVER=OFF \
-DCMAKE_SYSTEM_NAME=visionOS \
-DCMAKE_OSX_DEPLOYMENT_TARGET=1.0 \
-DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
macos-latest-swift:
runs-on: macos-latest
needs: macos-latest-ios-xcode
strategy:
matrix:
destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS']
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
# TODO: this likely does not do anything - if yes, remove it
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: apple-swift
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Download xcframework artifact
uses: actions/download-artifact@v7
with:
name: llama-xcframework
path: build-apple/llama.xcframework/
- name: Build llama.cpp with CMake
id: cmake_build
run: |
sysctl -a
cmake -B build -G Xcode \
-DGGML_METAL_USE_BF16=ON \
-DGGML_METAL_EMBED_LIBRARY=ON \
-DLLAMA_OPENSSL=OFF \
-DLLAMA_BUILD_APP=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_SERVER=OFF \
-DCMAKE_OSX_ARCHITECTURES="arm64;x86_64"
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
.github/workflows/build-cache.yml
+145
View File
@@ -0,0 +1,145 @@
name: Build Actions Cache
on:
workflow_dispatch: # allows manual triggering
schedule:
- cron: '0 * * * *'
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
jobs:
ubuntu-24-vulkan-cache:
runs-on: ubuntu-24.04
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Get latest Vulkan SDK version
id: vulkan_sdk_version
run: |
echo "VULKAN_SDK_VERSION=$(curl https://vulkan.lunarg.com/sdk/latest/linux.txt)" >> "$GITHUB_ENV"
- name: Setup Cache
uses: actions/cache@v5
id: cache-sdk
with:
path: ./vulkan_sdk
key: cache-gha-vulkan-sdk-${{ env.VULKAN_SDK_VERSION }}-${{ runner.os }}
- name: Setup Vulkan SDK
if: steps.cache-sdk.outputs.cache-hit != 'true'
uses: ./.github/actions/linux-setup-vulkan
with:
path: ./vulkan_sdk
version: ${{ env.VULKAN_SDK_VERSION }}
#ubuntu-24-spacemit-cache:
# runs-on: ubuntu-24.04
# env:
# # Make sure this is in sync with build-linux-cross.yml
# SPACEMIT_IME_TOOLCHAIN_VERSION: "1.1.2"
# steps:
# - name: Clone
# id: checkout
# uses: actions/checkout@v6
# - name: Setup Cache
# uses: actions/cache@v5
# id: cache-toolchain
# with:
# path: ./spacemit_toolchain
# key: cache-gha-spacemit-ime-toolchain-v${{ env.SPACEMIT_IME_TOOLCHAIN_VERSION }}-${{ runner.os }}
# - name: Setup SpacemiT Toolchain
# if: steps.cache-toolchain.outputs.cache-hit != 'true'
# uses: ./.github/actions/linux-setup-spacemit
# with:
# path: ./spacemit_toolchain
# version: ${{ env.SPACEMIT_IME_TOOLCHAIN_VERSION }}
ubuntu-24-openvino-cache:
runs-on: ubuntu-24.04
env:
# Sync versions in build.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
OPENVINO_VERSION_MAJOR: "2026.2.1"
OPENVINO_VERSION_FULL: "2026.2.1.21919.ede283a88e3"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Setup Cache
uses: actions/cache@v5
id: cache-openvino
with:
path: ./openvino_toolkit
key: cache-gha-openvino-toolkit-v${{ env.OPENVINO_VERSION_FULL }}-${{ runner.os }}
- name: Setup OpenVINO Toolkit
if: steps.cache-openvino.outputs.cache-hit != 'true'
uses: ./.github/actions/linux-setup-openvino
with:
path: ./openvino_toolkit
version_major: ${{ env.OPENVINO_VERSION_MAJOR }}
version_full: ${{ env.OPENVINO_VERSION_FULL }}
windows-2022-openvino-cache:
runs-on: windows-2022
env:
# Sync versions in build.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
OPENVINO_VERSION_MAJOR: "2026.2.1"
OPENVINO_VERSION_FULL: "2026.2.1.21919.ede283a88e3"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Setup Cache
uses: actions/cache@v5
id: cache-openvino
with:
path: ./openvino_toolkit
key: cache-gha-openvino-toolkit-v${{ env.OPENVINO_VERSION_FULL }}-${{ runner.os }}
- name: Setup OpenVINO Toolkit
if: steps.cache-openvino.outputs.cache-hit != 'true'
uses: ./.github/actions/windows-setup-openvino
with:
path: ./openvino_toolkit
version_major: ${{ env.OPENVINO_VERSION_MAJOR }}
version_full: ${{ env.OPENVINO_VERSION_FULL }}
windows-2022-rocm-cache:
runs-on: windows-2022
env:
# Make sure this is in sync with build.yml
HIPSDK_INSTALLER_VERSION: "26.Q1"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Setup Cache
uses: actions/cache@v5
id: cache-rocm
with:
path: C:\Program Files\AMD\ROCm
key: cache-gha-rocm-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ runner.os }}
- name: Setup ROCm
if: steps.cache-rocm.outputs.cache-hit != 'true'
uses: ./.github/actions/windows-setup-rocm
with:
version: ${{ env.HIPSDK_INSTALLER_VERSION }}
.github/workflows/build-cann.yml
+104
View File
@@ -0,0 +1,104 @@
name: CI (cann)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-cann.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-cann.yml',
'ggml/src/ggml-cann/**'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
# TODO: this build is disabled to save Github Actions resources (https://github.com/ggml-org/llama.cpp/pull/23705)
# in order to enable it again, we have to provision dedicated runners to run it
# openEuler-latest-cann:
# defaults:
# run:
# shell: bash -el {0}
# strategy:
# matrix:
# arch: [x86, aarch64]
# chip_type: ['910b', '310p']
# build: ['Release']
# use_acl_graph: ['on', 'off']
# exclude:
# # 310P does not support USE_ACL_GRAPH=on
# - chip_type: '310p'
# use_acl_graph: 'on'
# runs-on: ${{ matrix.arch == 'aarch64' && 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
# steps:
# - name: Checkout
# uses: actions/checkout@v6
# with:
# fetch-depth: 0
#
# - name: Free up disk space
# uses: ggml-org/free-disk-space@v1.3.1
# with:
# tool-cache: true
#
# - name: Set container image
# id: cann-image
# run: |
# image="ascendai/cann:${{ matrix.chip_type == '910b' && '8.5.0-910b-openeuler24.03-py3.11' || '8.5.0-310p-openeuler24.03-py3.11' }}"
# echo "image=${image}" >> "${GITHUB_OUTPUT}"
#
# - name: Pull container image
# run: docker pull "${{ steps.cann-image.outputs.image }}"
#
# - name: Build
# env:
# BUILD_TYPE: ${{ matrix.build }}
# SOC_TYPE: ascend${{ matrix.chip_type }}
# USE_ACL_GRAPH: ${{ matrix.use_acl_graph }}
# run: |
# HOST_UID=$(id -u)
# HOST_GID=$(id -g)
#
# docker run --rm \
# -v "${PWD}:/workspace" \
# -w /workspace \
# -e SOC_TYPE=${SOC_TYPE} \
# -e BUILD_TYPE=${BUILD_TYPE} \
# -e USE_ACL_GRAPH=${USE_ACL_GRAPH} \
# "${{ steps.cann-image.outputs.image }}" \
# bash -lc '
# set -e
# yum install -y --setopt=install_weak_deps=False --setopt=tsflags=nodocs git gcc gcc-c++ make cmake openssl-devel
# yum clean all && rm -rf /var/cache/yum
# git config --global --add safe.directory "/workspace"
# export LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:${ASCEND_TOOLKIT_HOME}/$(uname -m)-linux/devlib/:${LD_LIBRARY_PATH}
# cmake -S . -B build \
# -DCMAKE_BUILD_TYPE=${BUILD_TYPE} \
# -DGGML_CANN=on \
# -DSOC_TYPE=${SOC_TYPE} \
# -DUSE_ACL_GRAPH=${USE_ACL_GRAPH}
# cmake --build build -j $(nproc)
#
# chown -R '"${HOST_UID}"':'"${HOST_GID}"' /workspace/build
# '
.github/workflows/build-cmake-pkg.yml
+51
View File
@@ -0,0 +1,51 @@
name: Build relocatable cmake package
on:
workflow_dispatch:
workflow_call:
jobs:
linux:
runs-on: [self-hosted, Linux, CPU]
steps:
- uses: actions/checkout@v6
with:
fetch-depth: 0
- name: Build
run: |
PREFIX="$(pwd)"/inst
cmake -S . -B build \
-DCMAKE_PREFIX_PATH="$PREFIX" \
-DLLAMA_OPENSSL=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_APP=OFF \
-DCMAKE_BUILD_TYPE=Release
cmake --build build --config Release
cmake --install build --prefix "$PREFIX" --config Release
export LLAMA_CONFIG="$PREFIX"/lib/cmake/llama/llama-config.cmake
tclsh <<'EOF'
set build(commit) [string trim [exec git rev-parse --short HEAD]]
set build(number) [string trim [exec git rev-list --count HEAD]]
set build(version) "0.0.$build(number)"
set llamaconfig [read [open "$env(LLAMA_CONFIG)" r]]
set checks [list "set\\(LLAMA_VERSION \\s+$build(version)\\)" \
"set\\(LLAMA_BUILD_COMMIT\\s+$build(commit)\\)" \
"set\\(LLAMA_BUILD_NUMBER\\s+$build(number)\\)"]
puts -nonewline "Checking llama-config.cmake version... "
foreach check $checks {
if {![regexp -expanded -- $check $llamaconfig]} {
puts "\"$check\" failed!"
exit 1
}
}
puts "success."
EOF
cd examples/simple-cmake-pkg
cmake -S . -B build -DCMAKE_PREFIX_PATH="$PREFIX"/lib/cmake
cmake --build build
.github/workflows/build-cpu.yml
+215
View File
@@ -0,0 +1,215 @@
name: CI (cpu)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-cpu.yml',
'.github/workflows/build-cmake-pkg.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-cpu.yml',
'.github/workflows/build-cmake-pkg.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
build-cmake-pkg:
uses: ./.github/workflows/build-cmake-pkg.yml
ubuntu:
strategy:
matrix:
include:
- build: 'x64'
os: ubuntu-22.04
- build: 'arm64'
os: ubuntu-24.04-arm
runs-on: ${{ matrix.os }}
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: cpu-${{ matrix.os }}
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build Dependencies
id: build_depends
run: |
sudo apt-get update
sudo apt-get install -y --no-install-recommends \
python3 python3-pip python3-dev python3-wheel \
libjpeg-dev build-essential libssl-dev \
git-lfs
- name: Toolchain workaround (GCC 14)
if: ${{ contains(matrix.os, 'ubuntu-24.04') }}
run: |
sudo apt-get install -y gcc-14 g++-14
echo "CC=gcc-14" >> "$GITHUB_ENV"
echo "CXX=g++-14" >> "$GITHUB_ENV"
- name: Python Dependencies
id: python_depends
run: |
export PIP_BREAK_SYSTEM_PACKAGES="1"
python3 -m pip install --upgrade pip setuptools
pip3 install ./gguf-py
- name: Build
id: cmake_build
run: |
cmake -B build \
-DLLAMA_FATAL_WARNINGS=ON \
-DGGML_RPC=ON
time cmake --build build --config Release -j $(nproc)
- name: Test
id: cmake_test
run: |
cd build
ctest -L main --verbose --timeout 900
- name: Test llama2c conversion
id: llama2c_test
run: |
cd build
echo "Fetch tokenizer"
wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin
echo "Fetch llama2c model"
wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin
./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf
./bin/llama-completion -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
windows:
runs-on: windows-2025
env:
OPENBLAS_VERSION: 0.3.23
SDE_VERSION: 9.33.0-2024-01-07
VULKAN_VERSION: 1.4.313.2
strategy:
matrix:
include:
- build: 'x64-cpu-static'
arch: 'x64'
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DBUILD_SHARED_LIBS=OFF'
- build: 'x64-openblas'
arch: 'x64'
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_OPENMP=OFF -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
- build: 'x64-vulkan'
arch: 'x64'
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_VULKAN=ON'
- build: 'arm64'
arch: 'arm64'
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON'
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: cpu-windows-2025-${{ matrix.build }}
variant: ccache
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Download OpenBLAS
id: get_openblas
if: ${{ matrix.build == 'x64-openblas' }}
run: |
curl.exe -o $env:RUNNER_TEMP/openblas.zip -L "https://github.com/xianyi/OpenBLAS/releases/download/v${env:OPENBLAS_VERSION}/OpenBLAS-${env:OPENBLAS_VERSION}-x64.zip"
curl.exe -o $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt -L "https://github.com/xianyi/OpenBLAS/raw/v${env:OPENBLAS_VERSION}/LICENSE"
mkdir $env:RUNNER_TEMP/openblas
tar.exe -xvf $env:RUNNER_TEMP/openblas.zip -C $env:RUNNER_TEMP/openblas
$vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath)
$msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim()))
$lib = $(join-path $msvc 'bin\Hostx64\x64\lib.exe')
& $lib /machine:x64 "/def:${env:RUNNER_TEMP}/openblas/lib/libopenblas.def" "/out:${env:RUNNER_TEMP}/openblas/lib/openblas.lib" /name:openblas.dll
- name: Install Vulkan SDK
id: get_vulkan
if: ${{ matrix.build == 'x64-vulkan' }}
run: |
curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/vulkansdk-windows-X64-${env:VULKAN_VERSION}.exe"
& "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install
Add-Content $env:GITHUB_ENV "VULKAN_SDK=C:\VulkanSDK\${env:VULKAN_VERSION}"
Add-Content $env:GITHUB_PATH "C:\VulkanSDK\${env:VULKAN_VERSION}\bin"
- name: Install Ninja
id: install_ninja
run: |
choco install ninja
- name: Build
id: cmake_build
run: |
cmake -S . -B build ${{ matrix.defines }} `
-DLLAMA_BUILD_BORINGSSL=ON
cmake --build build --config Release -j ${env:NUMBER_OF_PROCESSORS}
- name: Add libopenblas.dll
id: add_libopenblas_dll
if: ${{ matrix.build == 'x64-openblas' }}
run: |
cp $env:RUNNER_TEMP/openblas/bin/libopenblas.dll ./build/bin/Release/openblas.dll
cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/bin/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt
- name: Test
id: cmake_test
if: ${{ matrix.arch == 'x64' }}
run: |
cd build
ctest -L main -C Release --verbose --timeout 900
# TODO: disabled for now, consider adding tests for all CPU variants instead
# - name: Test (Intel SDE)
# id: cmake_test_sde
# if: ${{ matrix.build == 'avx512-x64' && env.HAS_AVX512F == '0' }} # use Intel SDE for AVX-512 emulation
# run: |
# curl.exe -o $env:RUNNER_TEMP/sde.tar.xz -L "https://downloadmirror.intel.com/813591/sde-external-${env:SDE_VERSION}-win.tar.xz"
# # for some weird reason windows tar doesn't like sde tar.xz
# 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar.xz
# 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar
# $sde = $(join-path $env:RUNNER_TEMP sde-external-${env:SDE_VERSION}-win/sde.exe)
# cd build
# $env:LLAMA_SKIP_TESTS_SLOW_ON_EMULATOR = 1
# & $sde -future -- ctest -L main -C Release --verbose --timeout 900
.github/workflows/build-cross.yml
+317
View File
@@ -0,0 +1,317 @@
name: CI (cross)
on:
# only manual triggers due to low-importance of the workflows
# TODO: for regular runs, provision dedicated self-hosted runners
workflow_dispatch:
push:
branches:
- master
paths: [
'.github/workflows/build-cross.yml',
'ggml/src/spacemit/*',
'ggml/src/arch/loongarch/*'
]
# run once every week
schedule:
- cron: '0 0 * * 0'
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
jobs:
# ubuntu-24-riscv64-cpu-cross:
# runs-on: ubuntu-24.04
# steps:
# - uses: actions/checkout@v6
# - name: Setup Riscv
# run: |
# sudo dpkg --add-architecture riscv64
# # Add arch-specific repositories for non-amd64 architectures
# cat << EOF | sudo tee /etc/apt/sources.list.d/riscv64-ports.list
# deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble main universe
# deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble-updates main universe
# deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble-security main universe
# deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble-backports main universe
# EOF
# sudo apt-get update || true ;# Prevent failure due to missing URLs.
# sudo apt-get install -y --no-install-recommends \
# build-essential \
# gcc-14-riscv64-linux-gnu \
# g++-14-riscv64-linux-gnu
# - name: Build
# run: |
# cmake -B build -DLLAMA_OPENSSL=OFF \
# -DCMAKE_BUILD_TYPE=Release \
# -DGGML_OPENMP=OFF \
# -DLLAMA_BUILD_EXAMPLES=ON \
# -DLLAMA_BUILD_TOOLS=ON \
# -DLLAMA_BUILD_TESTS=OFF \
# -DCMAKE_SYSTEM_NAME=Linux \
# -DCMAKE_SYSTEM_PROCESSOR=riscv64 \
# -DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
# -DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14 \
# -DCMAKE_POSITION_INDEPENDENT_CODE=ON \
# -DCMAKE_FIND_ROOT_PATH=/usr/lib/riscv64-linux-gnu \
# -DCMAKE_FIND_ROOT_PATH_MODE_PROGRAM=NEVER \
# -DCMAKE_FIND_ROOT_PATH_MODE_LIBRARY=ONLY \
# -DCMAKE_FIND_ROOT_PATH_MODE_INCLUDE=BOTH
# cmake --build build --config Release -j $(nproc)
# ubuntu-24-riscv64-vulkan-cross:
# runs-on: ubuntu-24.04
# steps:
# - uses: actions/checkout@v6
# - name: Setup Riscv
# run: |
# sudo dpkg --add-architecture riscv64
# # Add arch-specific repositories for non-amd64 architectures
# cat << EOF | sudo tee /etc/apt/sources.list.d/riscv64-ports.list
# deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble main universe
# deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble-updates main universe
# deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble-security main universe
# deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble-backports main universe
# EOF
# sudo apt-get update || true ;# Prevent failure due to missing URLs.
# sudo apt-get install -y --no-install-recommends \
# build-essential \
# glslc \
# gcc-14-riscv64-linux-gnu \
# g++-14-riscv64-linux-gnu \
# libvulkan-dev:riscv64
# - name: Build
# run: |
# cmake -B build -DLLAMA_OPENSSL=OFF \
# -DCMAKE_BUILD_TYPE=Release \
# -DGGML_VULKAN=ON \
# -DGGML_OPENMP=OFF \
# -DLLAMA_BUILD_EXAMPLES=ON \
# -DLLAMA_BUILD_TOOLS=ON \
# -DLLAMA_BUILD_TESTS=OFF \
# -DCMAKE_SYSTEM_NAME=Linux \
# -DCMAKE_SYSTEM_PROCESSOR=riscv64 \
# -DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
# -DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14 \
# -DCMAKE_POSITION_INDEPENDENT_CODE=ON \
# -DCMAKE_FIND_ROOT_PATH=/usr/lib/riscv64-linux-gnu \
# -DCMAKE_FIND_ROOT_PATH_MODE_PROGRAM=NEVER \
# -DCMAKE_FIND_ROOT_PATH_MODE_LIBRARY=ONLY \
# -DCMAKE_FIND_ROOT_PATH_MODE_INCLUDE=BOTH
# cmake --build build --config Release -j $(nproc)
# ubuntu-24-arm64-vulkan-cross:
# runs-on: ubuntu-24.04
# steps:
# - uses: actions/checkout@v6
# - name: Setup Arm64
# run: |
# sudo dpkg --add-architecture arm64
# # Add arch-specific repositories for non-amd64 architectures
# cat << EOF | sudo tee /etc/apt/sources.list.d/arm64-ports.list
# deb [arch=arm64] http://ports.ubuntu.com/ubuntu-ports/ noble main universe
# deb [arch=arm64] http://ports.ubuntu.com/ubuntu-ports/ noble-updates main universe
# deb [arch=arm64] http://ports.ubuntu.com/ubuntu-ports/ noble-security main universe
# deb [arch=arm64] http://ports.ubuntu.com/ubuntu-ports/ noble-backports main universe
# EOF
# sudo apt-get update || true ;# Prevent failure due to missing URLs.
# sudo apt-get install -y --no-install-recommends \
# build-essential \
# glslc \
# crossbuild-essential-arm64 \
# libvulkan-dev:arm64
# - name: Build
# run: |
# cmake -B build -DLLAMA_OPENSSL=OFF \
# -DCMAKE_BUILD_TYPE=Release \
# -DGGML_VULKAN=ON \
# -DGGML_OPENMP=OFF \
# -DLLAMA_BUILD_EXAMPLES=ON \
# -DLLAMA_BUILD_TOOLS=ON \
# -DLLAMA_BUILD_TESTS=OFF \
# -DCMAKE_SYSTEM_NAME=Linux \
# -DCMAKE_SYSTEM_PROCESSOR=aarch64 \
# -DCMAKE_C_COMPILER=aarch64-linux-gnu-gcc \
# -DCMAKE_CXX_COMPILER=aarch64-linux-gnu-g++ \
# -DCMAKE_POSITION_INDEPENDENT_CODE=ON \
# -DCMAKE_FIND_ROOT_PATH=/usr/lib/aarch64-linux-gnu \
# -DCMAKE_FIND_ROOT_PATH_MODE_PROGRAM=NEVER \
# -DCMAKE_FIND_ROOT_PATH_MODE_LIBRARY=ONLY \
# -DCMAKE_FIND_ROOT_PATH_MODE_INCLUDE=BOTH
# cmake --build build --config Release -j $(nproc)
debian-13-loongarch64-cpu-cross:
runs-on: ${{ 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
container: debian@sha256:653dfb9f86c3782e8369d5f7d29bb8faba1f4bff9025db46e807fa4c22903671
steps:
- uses: actions/checkout@v6
- name: Setup LoongArch
run: |
rm -f /etc/apt/sources.list.d/*
cat << EOF | tee /etc/apt/sources.list.d/debian-ports.list
deb http://snapshot.debian.org/archive/debian/20250515T202920Z/ trixie main
EOF
( echo 'quiet "true";'; \
echo 'APT::Get::Assume-Yes "true";'; \
echo 'APT::Install-Recommends "false";'; \
echo 'Acquire::Check-Valid-Until "false";'; \
echo 'Acquire::Retries "5";'; \
) > /etc/apt/apt.conf.d/99snapshot-repos
apt-get update
apt-get install -y ca-certificates debian-ports-archive-keyring cmake git zip
dpkg --add-architecture loong64
# Add arch-specific repositories for non-amd64 architectures
cat << EOF | tee /etc/apt/sources.list.d/loong64-ports.list
deb [arch=loong64] http://snapshot.debian.org/archive/debian-ports/20250515T194251Z/ sid main
EOF
apt-get update || true ;# Prevent failure due to missing URLs.
apt-get install -y --no-install-recommends \
build-essential \
gcc-14-loongarch64-linux-gnu \
g++-14-loongarch64-linux-gnu
- name: Build
run: |
cmake -B build -DLLAMA_OPENSSL=OFF \
-DCMAKE_BUILD_TYPE=Release \
-DGGML_OPENMP=OFF \
-DLLAMA_BUILD_EXAMPLES=ON \
-DLLAMA_BUILD_TOOLS=ON \
-DLLAMA_BUILD_TESTS=OFF \
-DCMAKE_SYSTEM_NAME=Linux \
-DCMAKE_SYSTEM_PROCESSOR=loongarch64 \
-DCMAKE_C_COMPILER=loongarch64-linux-gnu-gcc-14 \
-DCMAKE_CXX_COMPILER=loongarch64-linux-gnu-g++-14 \
-DCMAKE_POSITION_INDEPENDENT_CODE=ON \
-DCMAKE_FIND_ROOT_PATH=/usr/lib/loongarch64-linux-gnu \
-DCMAKE_FIND_ROOT_PATH_MODE_PROGRAM=NEVER \
-DCMAKE_FIND_ROOT_PATH_MODE_LIBRARY=ONLY \
-DCMAKE_FIND_ROOT_PATH_MODE_INCLUDE=BOTH
cmake --build build --config Release -j $(nproc)
debian-13-loongarch64-vulkan-cross:
runs-on: ${{ 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
container: debian@sha256:653dfb9f86c3782e8369d5f7d29bb8faba1f4bff9025db46e807fa4c22903671
steps:
- uses: actions/checkout@v6
- name: Setup LoongArch
run: |
rm -f /etc/apt/sources.list.d/*
cat << EOF | tee /etc/apt/sources.list.d/debian-ports.list
deb http://snapshot.debian.org/archive/debian/20250515T202920Z/ trixie main
EOF
( echo 'quiet "true";'; \
echo 'APT::Get::Assume-Yes "true";'; \
echo 'APT::Install-Recommends "false";'; \
echo 'Acquire::Check-Valid-Until "false";'; \
echo 'Acquire::Retries "5";'; \
) > /etc/apt/apt.conf.d/99snapshot-repos
apt-get update
apt-get install -y ca-certificates debian-ports-archive-keyring cmake git zip
dpkg --add-architecture loong64
# Add arch-specific repositories for non-amd64 architectures
cat << EOF | tee /etc/apt/sources.list.d/loong64-ports.list
deb [arch=loong64] http://snapshot.debian.org/archive/debian-ports/20250515T194251Z/ sid main
EOF
apt-get update || true ;# Prevent failure due to missing URLs.
apt-get install -y --no-install-recommends \
build-essential \
glslc \
spirv-headers \
gcc-14-loongarch64-linux-gnu \
g++-14-loongarch64-linux-gnu \
libvulkan-dev:loong64
- name: Build
run: |
cmake -B build -DLLAMA_OPENSSL=OFF \
-DCMAKE_BUILD_TYPE=Release \
-DGGML_VULKAN=ON \
-DGGML_OPENMP=OFF \
-DLLAMA_BUILD_EXAMPLES=ON \
-DLLAMA_BUILD_TOOLS=ON \
-DLLAMA_BUILD_TESTS=OFF \
-DCMAKE_SYSTEM_NAME=Linux \
-DCMAKE_SYSTEM_PROCESSOR=loongarch64 \
-DCMAKE_C_COMPILER=loongarch64-linux-gnu-gcc-14 \
-DCMAKE_CXX_COMPILER=loongarch64-linux-gnu-g++-14 \
-DCMAKE_POSITION_INDEPENDENT_CODE=ON \
-DCMAKE_FIND_ROOT_PATH=/usr/lib/loongarch64-linux-gnu \
-DCMAKE_FIND_ROOT_PATH_MODE_PROGRAM=NEVER \
-DCMAKE_FIND_ROOT_PATH_MODE_LIBRARY=ONLY \
-DCMAKE_FIND_ROOT_PATH_MODE_INCLUDE=BOTH
cmake --build build --config Release -j $(nproc)
ubuntu-24-riscv64-cpu-spacemit-ime-cross:
runs-on: ubuntu-24.04
env:
# Make sure this is in sync with build-cache.yml
SPACEMIT_IME_TOOLCHAIN_VERSION: "1.2.4"
steps:
- uses: actions/checkout@v6
#- name: Use SpacemiT Toolchain Cache
# uses: actions/cache@v5
# id: cache-toolchain
# with:
# path: ./spacemit_toolchain
# key: cache-gha-spacemit-ime-toolchain-v${{ env.SPACEMIT_IME_TOOLCHAIN_VERSION }}-${{ runner.os }}
- name: Setup SpacemiT Toolchain
#if: steps.cache-toolchain.outputs.cache-hit != 'true'
uses: ./.github/actions/linux-setup-spacemit
with:
path: ./spacemit_toolchain
version: ${{ env.SPACEMIT_IME_TOOLCHAIN_VERSION }}
- name: Build
run: |
export RISCV_ROOT_PATH=${PWD}/spacemit_toolchain
cmake -B build -DLLAMA_OPENSSL=OFF \
-DCMAKE_BUILD_TYPE=Release \
-DLLAMA_BUILD_EXAMPLES=ON \
-DGGML_CPU_REPACK=OFF \
-DLLAMA_BUILD_TOOLS=ON \
-DLLAMA_BUILD_TESTS=OFF \
-DGGML_CPU_RISCV64_SPACEMIT=ON \
-DGGML_RVV=ON \
-DGGML_RV_ZVFH=ON \
-DGGML_RV_ZFH=ON \
-DGGML_RV_ZICBOP=ON \
-DGGML_RV_ZIHINTPAUSE=ON \
-DGGML_RV_ZBA=ON \
-DCMAKE_TOOLCHAIN_FILE=${PWD}/cmake/riscv64-spacemit-linux-gnu-gcc.cmake
cmake --build build --config Release -j $(nproc)
.github/workflows/build-cuda-ubuntu.yml
+134
View File
@@ -0,0 +1,134 @@
name: CI (CUDA, ubuntu)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-cuda-ubuntu.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.cu',
'**/*.cuh'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-cuda-ubuntu.yml',
'ggml/src/ggml-cuda/**'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
cuda:
runs-on: ubuntu-24.04
container: nvidia/cuda:12.6.2-devel-ubuntu24.04
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Install dependencies
env:
DEBIAN_FRONTEND: noninteractive
run: |
apt update
apt install -y cmake build-essential ninja-build libgomp1 git libssl-dev
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: cuda-ubuntu-24.04-cuda
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build with CMake
# TODO: Remove GGML_CUDA_CUB_3DOT2 flag once CCCL 3.2 is bundled within CTK and that CTK version is used in this project
run: |
cmake -S . -B build -G Ninja \
-DLLAMA_FATAL_WARNINGS=ON \
-DCMAKE_BUILD_TYPE=Release \
-DCMAKE_CUDA_ARCHITECTURES=89-real \
-DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined \
-DGGML_NATIVE=OFF \
-DGGML_CUDA=ON \
-DGGML_CUDA_CUB_3DOT2=ON
cmake --build build
hip:
runs-on: ubuntu-22.04
container: rocm/dev-ubuntu-22.04:6.1.2
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libssl-dev rocwmma-dev
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: cuda-ubuntu-22.04-hip
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build with native CMake HIP support
id: cmake_build
run: |
cmake -B build -S . \
-DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \
-DGGML_HIP_ROCWMMA_FATTN=ON \
-DGPU_TARGETS="gfx1030" \
-DGGML_HIP=ON
cmake --build build --config Release -j $(nproc)
musa:
runs-on: ubuntu-22.04
container: mthreads/musa:rc4.3.0-devel-ubuntu22.04-amd64
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
apt-get update
apt-get install -y build-essential git cmake libssl-dev
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: cuda-ubuntu-22.04-musa
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build with native CMake MUSA support
id: cmake_build
run: |
cmake -B build -S . \
-DGGML_MUSA=ON
time cmake --build build --config Release -j $(nproc)
.github/workflows/build-cuda-windows.yml
+162
View File
@@ -0,0 +1,162 @@
name: CI (CUDA, windows)
# TODO: this workflow is only triggered manually because it is very heavy on the CI
# when we provision dedicated windows runners, we can enable it for pushes too
# note: running this workflow manually will populate the ccache for the release builds
# this can be used before merging a PR to speed up the release workflow
on:
workflow_dispatch: # allows manual triggering
# note: this will run in queue with the release workflow
concurrency:
group: release
queue: max
env:
GH_TOKEN: ${{ github.token }}
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
cuda:
runs-on: windows-2022
permissions:
actions: write
strategy:
matrix:
cuda: ['12.4', '13.3']
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: release-windows-2022-x64-cuda-${{ matrix.cuda }}
- name: Install Cuda Toolkit
uses: ./.github/actions/windows-setup-cuda
with:
cuda_version: ${{ matrix.cuda }}
- name: Install Ninja
id: install_ninja
run: |
choco install ninja
- name: Build
id: cmake_build
shell: cmd
# TODO: Remove GGML_CUDA_CUB_3DOT2 flag once CCCL 3.2 is bundled within CTK and that CTK version is used in this project
run: |
call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvarsall.bat" x64
cmake -S . -B build -G "Ninja Multi-Config" ^
-DLLAMA_BUILD_SERVER=ON ^
-DLLAMA_BUILD_BORINGSSL=ON ^
-DGGML_NATIVE=OFF ^
-DGGML_BACKEND_DL=ON ^
-DGGML_CPU_ALL_VARIANTS=ON ^
-DGGML_CUDA=ON ^
-DGGML_RPC=ON ^
-DGGML_CUDA_CUB_3DOT2=ON
set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1
cmake --build build --config Release -j %NINJA_JOBS% -t ggml
cmake --build build --config Release
- name: ccache-clear
uses: ./.github/actions/ccache-clear
with:
key: release-windows-2022-x64-cuda-${{ matrix.cuda }}
hip:
runs-on: windows-2022
permissions:
actions: write
env:
# Make sure this is in sync with build-cache.yml
HIPSDK_INSTALLER_VERSION: "26.Q1"
strategy:
matrix:
include:
# sync with release.yml
- name: "radeon"
gpu_targets: "gfx1150;gfx1151;gfx1200;gfx1201;gfx1100;gfx1101;gfx1102;gfx1030;gfx1031;gfx1032"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Grab rocWMMA package
id: grab_rocwmma
run: |
curl -o rocwmma.deb "https://repo.radeon.com/rocm/apt/7.2.1/pool/main/r/rocwmma-dev/rocwmma-dev_2.2.0.70201-81~24.04_amd64.deb"
7z x rocwmma.deb
7z x data.tar
- name: Use ROCm Installation Cache
uses: actions/cache@v5
id: cache-rocm
with:
path: C:\Program Files\AMD\ROCm
key: cache-gha-rocm-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ runner.os }}
- name: Setup ROCm
if: steps.cache-rocm.outputs.cache-hit != 'true'
uses: ./.github/actions/windows-setup-rocm
with:
version: ${{ env.HIPSDK_INSTALLER_VERSION }}
- name: Verify ROCm
id: verify
run: |
# Find and test ROCm installation
$clangPath = Get-ChildItem 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | Select-Object -First 1
if (-not $clangPath) {
Write-Error "ROCm installation not found"
exit 1
}
& $clangPath.FullName --version
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
# TODO: this build does not match the build in release.yml, so we use a different cache key
# ideally, the builds should match, similar to the CUDA build above so that we would be able
# to populate the ccache for the release with manual runs of this workflow
#key: release-windows-2022-x64-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}
key: cuda-windows-2022-x64-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}
- name: Build
id: cmake_build
run: |
$env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path)
$env:CMAKE_PREFIX_PATH="${env:HIP_PATH}"
cmake -G "Unix Makefiles" -B build -S . `
-DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" `
-DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" `
-DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/opt/rocm-7.2.1/include/" `
-DCMAKE_BUILD_TYPE=Release `
-DLLAMA_BUILD_BORINGSSL=ON `
-DROCM_DIR="${env:HIP_PATH}" `
-DGGML_HIP=ON `
-DGGML_HIP_ROCWMMA_FATTN=ON `
-DGPU_TARGETS="gfx1100" `
-DGGML_RPC=ON
cmake --build build -j ${env:NUMBER_OF_PROCESSORS}
- name: ccache-clear
uses: ./.github/actions/ccache-clear
with:
#key: release-windows-2022-x64-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}
key: cuda-windows-2022-x64-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}
.github/workflows/build-ibm.yml
+150
View File
@@ -0,0 +1,150 @@
name: CI (ibm)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-ibm.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-ibm.yml',
'ggml/src/ggml-cpu/**'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu-24-s390x:
runs-on: ubuntu-24.04-s390x
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Build Dependencies
id: build_depends
run: |
sudo apt-get update
sudo apt-get install -y --no-install-recommends \
python3 python3-pip python3-dev python3-wheel \
libjpeg-dev build-essential libssl-dev \
git-lfs
- name: Toolchain workaround (GCC 14)
run: |
sudo apt-get install -y gcc-14 g++-14
echo "CC=gcc-14" >> "$GITHUB_ENV"
echo "CXX=g++-14" >> "$GITHUB_ENV"
- name: Python Dependencies
id: python_depends
run: |
export PIP_BREAK_SYSTEM_PACKAGES="1"
python3 -m pip install --upgrade pip setuptools
pip3 install ./gguf-py
- name: Swap Endianness
id: endianness
run: |
for f in models/*.gguf; do
echo YES | python3 gguf-py/gguf/scripts/gguf_convert_endian.py $f big
done
- name: Build
id: cmake_build
run: |
cmake -B build \
-DLLAMA_FATAL_WARNINGS=ON \
-DGGML_RPC=ON
time cmake --build build --config Release -j $(nproc)
- name: Test
id: cmake_test
run: |
cd build
ctest -L main --verbose --timeout 900
- name: Test llama2c (s390x)
id: llama2c_test_s390x
run: |
cd build
echo "Fetch llama2c big-endian model"
wget https://huggingface.co/ggml-org/models/resolve/main/tinyllamas/stories260K-be.gguf
./bin/llama-completion -m stories260K-be.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
ubuntu-24-ppc64le:
runs-on: ubuntu-24.04-ppc64le
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Build Dependencies
id: build_depends
run: |
sudo apt-get update
sudo apt-get install -y --no-install-recommends \
python3 python3-pip python3-dev python3-wheel \
libjpeg-dev build-essential libssl-dev \
git-lfs
- name: Toolchain workaround (GCC 14)
run: |
sudo apt-get install -y gcc-14 g++-14
echo "CC=gcc-14" >> "$GITHUB_ENV"
echo "CXX=g++-14" >> "$GITHUB_ENV"
- name: Python Dependencies
id: python_depends
run: |
export PIP_BREAK_SYSTEM_PACKAGES="1"
python3 -m pip install --upgrade pip setuptools
pip3 install ./gguf-py
- name: Build
id: cmake_build
run: |
cmake -B build \
-DLLAMA_FATAL_WARNINGS=ON \
-DGGML_RPC=ON
time cmake --build build --config Release -j $(nproc)
- name: Test
id: cmake_test
run: |
cd build
ctest -L main --verbose --timeout 900
- name: Test llama2c conversion
id: llama2c_test
run: |
cd build
echo "Fetch tokenizer"
wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin
echo "Fetch llama2c model"
wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin
./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf
./bin/llama-completion -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
.github/workflows/build-msys.yml
+70
View File
@@ -0,0 +1,70 @@
name: CI (msys)
on:
# only manual triggers due to low-importance of the workflows
# TODO: for regular runs, provision dedicated self-hosted runners
workflow_dispatch:
# run once every week
schedule:
- cron: '0 0 * * 0'
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
windows-msys2:
runs-on: windows-2025
strategy:
fail-fast: false
matrix:
include:
- { sys: UCRT64, env: ucrt-x86_64, compiler: gcc, build: Release }
- { sys: CLANG64, env: clang-x86_64, compiler: clang, build: Release }
steps:
- name: Clone
uses: actions/checkout@v6
#- name: ccache
# uses: ggml-org/ccache-action@v1.2.16
# with:
# key: msys-windows-2025-x64
# variant: ccache
# evict-old-files: 1d
# save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Setup ${{ matrix.sys }}
uses: msys2/setup-msys2@cafece8e6baf9247cf9b1bf95097b0b983cc558d # v2
with:
update: true
msystem: ${{matrix.sys}}
install: >-
mingw-w64-${{matrix.env}}-${{matrix.compiler}}
mingw-w64-${{matrix.env}}-cmake
mingw-w64-${{matrix.env}}-openblas
- name: Build using CMake
shell: msys2 {0}
run: |
cmake -B build
cmake --build build --config ${{ matrix.build }} -j $(nproc)
- name: Clean after building using CMake
shell: msys2 {0}
run: |
rm -rf build
- name: Build using CMake w/ OpenBLAS
shell: msys2 {0}
run: |
cmake -B build -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
cmake --build build --config ${{ matrix.build }} -j $(nproc)
.github/workflows/build-opencl.yml
+82
View File
@@ -0,0 +1,82 @@
name: CI (opencl)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-opencl.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.cl'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-opencl.yml',
'ggml/src/ggml-opencl/**'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
windows-2025-opencl-adreno:
runs-on: windows-2025
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: opencl-windows-2025-x64
variant: ccache
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Install Ninja
id: install_ninja
run: |
choco install ninja
- name: Install OpenCL Headers and Libs
id: install_opencl
run: |
git clone https://github.com/KhronosGroup/OpenCL-Headers
cd OpenCL-Headers
cmake -B build `
-DBUILD_TESTING=OFF `
-DOPENCL_HEADERS_BUILD_TESTING=OFF `
-DOPENCL_HEADERS_BUILD_CXX_TESTS=OFF `
-DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release"
cmake --build build --target install
git clone https://github.com/KhronosGroup/OpenCL-ICD-Loader
cd OpenCL-ICD-Loader
cmake -B build-arm64-release `
-A arm64 `
-DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" `
-DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release"
cmake --build build-arm64-release --target install --config release
- name: Build
id: cmake_build
run: |
cmake -S . -B build -G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" -DGGML_OPENCL=ON -DGGML_OPENCL_USE_ADRENO_KERNELS=ON -DLLAMA_BUILD_BORINGSSL=ON
cmake --build build --config Release -j ${env:NUMBER_OF_PROCESSORS}
.github/workflows/build-openvino.yml
+169
View File
@@ -0,0 +1,169 @@
name: CI (openvino)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-openvino.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-openvino.yml',
'ggml/src/ggml-openvino/**'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu-24-openvino:
runs-on: [self-hosted, Linux, Intel, OpenVINO]
env:
# Sync versions in build-openvino.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
OPENVINO_VERSION_MAJOR: "2026.2.1"
OPENVINO_VERSION_FULL: "2026.2.1.21919.ede283a88e3"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install -y build-essential libssl-dev libtbb12 cmake ninja-build python3-pip
sudo apt-get install -y ocl-icd-opencl-dev opencl-headers opencl-clhpp-headers intel-opencl-icd
- name: Setup OpenVINO Toolkit
uses: ./.github/actions/linux-setup-openvino
with:
path: ./openvino_toolkit
version_major: ${{ env.OPENVINO_VERSION_MAJOR }}
version_full: ${{ env.OPENVINO_VERSION_FULL }}
- name: Install OpenVINO dependencies
run: |
cd ./openvino_toolkit
chmod +x ./install_dependencies/install_openvino_dependencies.sh
echo "Y" | sudo -E ./install_dependencies/install_openvino_dependencies.sh
- name: Build
id: cmake_build
run: |
source ./openvino_toolkit/setupvars.sh
cmake -B build/ReleaseOV -G Ninja \
-DCMAKE_BUILD_TYPE=Release \
-DGGML_OPENVINO=ON
time cmake --build build/ReleaseOV --config Release --parallel
- name: Test (CPU)
id: cmake_test_cpu
# TODO: fix and re-enable the `test-llama-archs` test below
run: |
cd ${{ github.workspace }}
ctest --test-dir build/ReleaseOV -L main -E "test-llama-archs" --verbose --timeout 2000
- name: Test (GPU)
id: cmake_test_gpu
# TODO: fix and re-enable the `test-llama-archs` test below
run: |
cd ${{ github.workspace }}
export GGML_OPENVINO_DEVICE=GPU
ctest --test-dir build/ReleaseOV -L main -E "test-llama-archs" --verbose --timeout 3000
openvino-windows-2022:
runs-on: windows-2022
env:
# Sync versions in build-openvino.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
OPENVINO_VERSION_MAJOR: "2026.2.1"
OPENVINO_VERSION_FULL: "2026.2.1.21919.ede283a88e3"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: openvino-windows-2022
variant: ccache
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Setup Cache
uses: actions/cache@v5
id: cache-openvino
with:
path: ./openvino_toolkit
key: cache-gha-openvino-toolkit-v${{ env.OPENVINO_VERSION_FULL }}-${{ runner.os }}
- name: Setup OpenVINO Toolkit
if: steps.cache-openvino.outputs.cache-hit != 'true'
uses: ./.github/actions/windows-setup-openvino
with:
path: ./openvino_toolkit
version_major: ${{ env.OPENVINO_VERSION_MAJOR }}
version_full: ${{ env.OPENVINO_VERSION_FULL }}
- name: Install OpenCL using vcpkg
shell: powershell
run: |
git clone https://github.com/microsoft/vcpkg C:\vcpkg
C:\vcpkg\bootstrap-vcpkg.bat
C:\vcpkg\vcpkg install opencl
- name: Build
id: cmake_build
shell: cmd
run: |
REM Find extracted OpenVINO folder dynamically
for /d %%i in (openvino_toolkit\*) do set OPENVINO_ROOT=%%i
if not exist "%OPENVINO_ROOT%\runtime\cmake\OpenVINOConfig.cmake" (
echo ERROR: OpenVINOConfig.cmake not found
exit /b 1
)
call "%OPENVINO_ROOT%\setupvars.bat"
cmake -B build\ReleaseOV -G "Visual Studio 17 2022" ^
-A x64 ^
-DCMAKE_BUILD_TYPE=Release ^
-DGGML_OPENVINO=ON ^
-DCMAKE_TOOLCHAIN_FILE=C:\vcpkg\scripts\buildsystems\vcpkg.cmake
cmake --build build\ReleaseOV --config Release -- /m
- name: Test (CPU)
id: cmake_test_cpu
shell: cmd
# TODO: fix and re-enable the `test-llama-archs` test below
run: |
REM Find extracted OpenVINO folder dynamically
for /d %%i in (openvino_toolkit\*) do set OPENVINO_ROOT=%%i
call "%OPENVINO_ROOT%\setupvars.bat"
cd build
ctest --test-dir ReleaseOV -L main -E "test-llama-archs" -C Release --verbose --timeout 3000
.github/workflows/build-riscv.yml
+188
View File
@@ -0,0 +1,188 @@
name: CI (riscv)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-riscv.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-riscv.yml',
'ggml/src/ggml-cpu/arch/riscv/**'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu-cpu-riscv64-native:
runs-on: ubuntu-24.04-riscv
steps:
- name: Install dependencies
run: |
# Install necessary packages
sudo apt-get update
sudo apt-get install -y libssl-dev
# Set gcc-14 and g++-14 as the default compilers
sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-14 100
sudo update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-14 100
git lfs install
- name: Check environment
run: |
uname -a
gcc --version
g++ --version
ldd --version
cmake --version
rustc --version
env
echo "nproc=$(nproc)"
- name: Clone
id: checkout
uses: actions/checkout@v6
# note: sparing some ccache since these jobs run on dedicated runners that are not part of the organitzation
#- name: ccache
# uses: ggml-org/ccache-action@afde29e5b5422e5da23cb1f639e8baecadeadfc3 # https://github.com/ggml-org/ccache-action/pull/1
# with:
# key: riscv-ubuntu-native
# evict-old-files: 1d
# save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
run: |
cmake -B build \
-DCMAKE_BUILD_TYPE=Release \
-DGGML_OPENMP=OFF \
-DLLAMA_BUILD_EXAMPLES=ON \
-DLLAMA_BUILD_TOOLS=ON \
-DLLAMA_BUILD_TESTS=ON \
-DCMAKE_C_COMPILER_LAUNCHER=ccache \
-DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
-DGGML_RPC=ON \
-DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
-DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14
time cmake --build build --config Release -j $(nproc)
- name: Test
id: cmake_test
run: |
cd build
ctest -L main --verbose --timeout 900
- name: Test llama2c conversion
id: llama2c_test
run: |
cd build
echo "Fetch tokenizer"
wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin
echo "Fetch llama2c model"
wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin
./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf
./bin/llama-completion -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
ubuntu-riscv64-native-sanitizer:
runs-on: ubuntu-24.04-riscv
continue-on-error: true
strategy:
matrix:
sanitizer: [ADDRESS, THREAD, UNDEFINED]
build_type: [Debug]
steps:
- name: Install dependencies
run: |
# Set gcc-14 and g++-14 as the default compilers
sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-14 100
sudo update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-14 100
git lfs install
- name: GCC version check
run: |
gcc --version
g++ --version
- name: Clone
id: checkout
uses: actions/checkout@v6
# note: sparing some ccache since these jobs run on dedicated runners that are not part of the organitzation
#- name: ccache
# uses: ggml-org/ccache-action@afde29e5b5422e5da23cb1f639e8baecadeadfc3 # https://github.com/ggml-org/ccache-action/pull/1
# with:
# key: riscv-ubuntu-native-sanitizer-${{ matrix.sanitizer }}-${{ matrix.build_type }}
# evict-old-files: 1d
# save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
if: ${{ matrix.sanitizer != 'THREAD' }}
run: |
cmake -B build \
-DLLAMA_OPENSSL=OFF \
-DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
-DGGML_OPENMP=ON \
-DLLAMA_BUILD_EXAMPLES=ON \
-DLLAMA_BUILD_TOOLS=ON \
-DLLAMA_BUILD_TESTS=OFF \
-DCMAKE_C_COMPILER_LAUNCHER=ccache \
-DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
-DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
-DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
-DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14
cmake --build build --config ${{ matrix.build_type }} -j $(nproc)
- name: Build (no OpenMP)
id: cmake_build_no_openmp
if: ${{ matrix.sanitizer == 'THREAD' }}
run: |
cmake -B build \
-DLLAMA_OPENSSL=OFF \
-DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
-DGGML_OPENMP=OFF \
-DLLAMA_BUILD_EXAMPLES=ON \
-DLLAMA_BUILD_TOOLS=ON \
-DLLAMA_BUILD_TESTS=OFF \
-DCMAKE_C_COMPILER_LAUNCHER=ccache \
-DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
-DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
-DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
-DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14
cmake --build build --config ${{ matrix.build_type }} -j $(nproc)
- name: Test
id: cmake_test
run: |
cd build
ctest -L main --verbose --timeout 900
.github/workflows/build-rpc.yml
+66
View File
@@ -0,0 +1,66 @@
name: CI (rpc)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-rpc.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-rpc.yml',
'ggml/src/ggml-rpc/**'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu-24-rpc:
runs-on: ${{ 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
continue-on-error: true
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install build-essential libssl-dev ninja-build
- name: Build
id: cmake_build
run: |
cmake -B build \
-G "Ninja" \
-DCMAKE_BUILD_TYPE=Release \
-DGGML_RPC=ON
time cmake --build build --config Release -j $(nproc)
- name: Test
id: cmake_test
run: |
cd build
ctest -L main --verbose
.github/workflows/build-sanitize.yml
+86
View File
@@ -0,0 +1,86 @@
name: CI (sanitize)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-sanitize.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ctest:
runs-on: [self-hosted, X64, CPU, Linux]
continue-on-error: true
strategy:
matrix:
sanitizer: [ADDRESS, THREAD, UNDEFINED]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
# with UNDEFINED sanitizer, we have to build in Debug to avoid GCC 13 false-positive warnings
- name: Build (undefined)
id: cmake_build_undefined
if: ${{ matrix.sanitizer == 'UNDEFINED' }}
run: |
cmake -B build \
-DCMAKE_BUILD_TYPE=Debug \
-DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
-DGGML_SANITIZE_${{ matrix.sanitizer }}=ON
cmake --build build --config Debug -j $(nproc)
- name: Build
id: cmake_build
if: ${{ matrix.sanitizer == 'ADDRESS' }}
run: |
cmake -B build \
-DCMAKE_BUILD_TYPE=RelWithDebInfo \
-DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
-DGGML_SANITIZE_${{ matrix.sanitizer }}=ON
cmake --build build --config RelWithDebInfo -j $(nproc)
- name: Build (no OpenMP)
id: cmake_build_no_openmp
if: ${{ matrix.sanitizer == 'THREAD' }}
run: |
cmake -B build \
-DCMAKE_BUILD_TYPE=RelWithDebInfo \
-DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
-DGGML_SANITIZE_${{ matrix.sanitizer }}=ON \
-DGGML_OPENMP=OFF
cmake --build build --config RelWithDebInfo -j $(nproc)
- name: Test
id: cmake_test
# skip run in Debug - very slow
if: ${{ matrix.sanitizer != 'UNDEFINED' }}
run: |
cd build
ctest -L main -E tokenizer --verbose --timeout 900
.github/workflows/build-self-hosted.yml
+387
View File
@@ -0,0 +1,387 @@
name: CI (self-hosted)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.cu',
'**/*.cuh',
'**/*.swift',
'**/*.m',
'**/*.metal',
'**/*.comp',
'**/*.glsl',
'**/*.wgsl'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-self-hosted.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.cu',
'**/*.cuh',
'**/*.swift',
'**/*.m',
'**/*.metal',
'**/*.comp',
'**/*.glsl',
'**/*.wgsl'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
gpu-cuda:
runs-on: [self-hosted, Linux, NVIDIA]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Test
id: ggml-ci
run: |
nvidia-smi
GG_BUILD_CUDA=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
gpu-vulkan-nvidia-cm:
runs-on: [self-hosted, Linux, NVIDIA]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Test
id: ggml-ci
run: |
vulkaninfo --summary
GG_BUILD_VULKAN=1 GGML_VK_DISABLE_COOPMAT2=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
gpu-vulkan-nvidia-cm2:
runs-on: [self-hosted, Linux, NVIDIA, COOPMAT2]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Test
id: ggml-ci
run: |
vulkaninfo --summary
GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
gpu-webgpu-nvidia:
runs-on: [self-hosted, Linux, NVIDIA, X64]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dawn Dependency
id: dawn-depends
run: |
DAWN_VERSION="v20260317.182325"
DAWN_OWNER="google"
DAWN_REPO="dawn"
DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-ubuntu-latest-Release"
echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
curl -L -o artifact.tar.gz \
"https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
mkdir dawn
tar -xvf artifact.tar.gz -C dawn --strip-components=1
- name: Test
id: ggml-ci
run: |
GG_BUILD_WEBGPU=1 \
GG_BUILD_WEBGPU_DAWN_PREFIX="$GITHUB_WORKSPACE/dawn" \
GG_BUILD_WEBGPU_DAWN_DIR="$GITHUB_WORKSPACE/dawn/lib64/cmake/Dawn" \
bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
# TODO: provision AMX-compatible machine
#cpu-amx:
# runs-on: [self-hosted, Linux, CPU, AMX]
# steps:
# - name: Clone
# id: checkout
# uses: actions/checkout@v6
# - name: Test
# id: ggml-ci
# run: |
# bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
# TODO: provision AMD GPU machine
# amd-vulkan:
# runs-on: [self-hosted, Linux, AMD]
# steps:
# - name: Clone
# id: checkout
# uses: actions/checkout@v6
# - name: Test
# id: ggml-ci
# run: |
# vulkaninfo --summary
# GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
# TODO: provision AMD GPU machine
# amd-rocm:
# runs-on: [self-hosted, Linux, AMD]
# steps:
# - name: Clone
# id: checkout
# uses: actions/checkout@v6
# - name: Test
# id: ggml-ci
# run: |
# amd-smi static
# GG_BUILD_ROCM=1 GG_BUILD_AMDGPU_TARGETS="gfx1101" bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
gpu-metal:
runs-on: [self-hosted, macOS, ARM64]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Test
id: ggml-ci
run: |
GG_BUILD_METAL=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
gpu-webgpu-apple:
runs-on: [self-hosted, macOS, ARM64]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dawn Dependency
id: dawn-depends
run: |
DAWN_VERSION="v20260317.182325"
DAWN_OWNER="google"
DAWN_REPO="dawn"
DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-macos-latest-Release"
echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
curl -L -o artifact.tar.gz \
"https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
mkdir dawn
tar -xvf artifact.tar.gz -C dawn --strip-components=1
- name: Test
id: ggml-ci
run: |
GG_BUILD_WEBGPU=1 GG_BUILD_WEBGPU_DAWN_PREFIX="$GITHUB_WORKSPACE/dawn" \
bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
gpu-vulkan-apple:
runs-on: [self-hosted, macOS, ARM64]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Test
id: ggml-ci
run: |
vulkaninfo --summary
GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
gpu-vulkan-intel-linux:
runs-on: [self-hosted, Linux, Intel]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
with:
persist-credentials: false
- name: Test
id: ggml-ci
run: |
vulkaninfo --summary
GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
gpu-vulkan-intel-windows:
runs-on: [self-hosted, Windows, X64, Intel]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Test
id: ggml-ci
shell: C:\msys64\usr\bin\bash.exe --noprofile --norc -eo pipefail "{0}"
env:
MSYSTEM: UCRT64
CHERE_INVOKING: 1
PATH: C:\msys64\ucrt64\bin;C:\msys64\usr\bin;C:\Windows\System32;${{ env.PATH }}
run: |
vulkaninfo --summary
# Skip python related tests with GG_BUILD_LOW_PERF=1 since Windows MSYS2 UCRT64 currently fails to create
# a valid python environment for testing
LLAMA_FATAL_WARNINGS=OFF GG_BUILD_NINJA=1 GG_BUILD_VULKAN=1 GG_BUILD_LOW_PERF=1 ./ci/run.sh ./results/llama.cpp ./mnt/llama.cpp
gpu-openvino-low-perf:
runs-on: [self-hosted, Linux, Intel, OpenVINO]
env:
# Sync versions in build.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
OPENVINO_VERSION_MAJOR: "2026.2.1"
OPENVINO_VERSION_FULL: "2026.2.1.21919.ede283a88e3"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Setup OpenVINO Toolkit
uses: ./.github/actions/linux-setup-openvino
with:
path: ./openvino_toolkit
version_major: ${{ env.OPENVINO_VERSION_MAJOR }}
version_full: ${{ env.OPENVINO_VERSION_FULL }}
- name: Install OpenVINO dependencies
run: |
cd ./openvino_toolkit
chmod +x ./install_dependencies/install_openvino_dependencies.sh
echo "Y" | sudo -E ./install_dependencies/install_openvino_dependencies.sh
- name: Test
id: ggml-ci
run: |
source ./openvino_toolkit/setupvars.sh
GG_BUILD_OPENVINO=1 GGML_OPENVINO_DEVICE=GPU GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
cpu-x64-high-perf:
runs-on: [self-hosted, Linux, X64]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Test
id: ggml-ci
run: |
LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
cpu-arm64-high-perf-graviton4:
runs-on: ah-ubuntu_22_04-c8g_8x
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
set -euxo pipefail
sudo apt-get update
sudo DEBIAN_FRONTEND=noninteractive NEEDRESTART_MODE=a \
apt-get install -y \
build-essential \
python3-venv \
gpg \
wget \
time \
git-lfs
git lfs install
# install the latest cmake
sudo install -d /usr/share/keyrings
wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc \
| gpg --dearmor \
| sudo tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null
echo 'deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ jammy main' \
| sudo tee /etc/apt/sources.list.d/kitware.list
sudo apt-get update
sudo apt-get install -y cmake
- name: Test
id: ggml-ci
run: |
LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
cpu-arm64-graviton4-kleidiai:
runs-on: ah-ubuntu_22_04-c8g_8x
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
set -euxo pipefail
sudo apt-get update
sudo DEBIAN_FRONTEND=noninteractive NEEDRESTART_MODE=a \
apt-get install -y \
build-essential \
python3-venv \
gpg \
wget \
time \
git-lfs
git lfs install
# install the latest cmake
sudo install -d /usr/share/keyrings
wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc \
| gpg --dearmor \
| sudo tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null
echo 'deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ jammy main' \
| sudo tee /etc/apt/sources.list.d/kitware.list
sudo apt-get update
sudo apt-get install -y cmake
- name: Test
id: ggml-ci
run: |
GG_BUILD_KLEIDIAI=1 \
GG_BUILD_EXTRA_TESTS_0=1 \
bash ./ci/run.sh ./tmp/results ./tmp/mnt
.github/workflows/build-sycl.yml
+141
View File
@@ -0,0 +1,141 @@
name: CI (sycl)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-sycl.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-sycl.yml',
'ggml/src/ggml-sycl/**'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu-24-sycl:
strategy:
matrix:
build: [fp32, fp16]
include:
- build: fp32
fp16: OFF
- build: fp16
fp16: ON
runs-on: ubuntu-24.04
env:
ONEAPI_ROOT: /opt/intel/oneapi/
ONEAPI_INSTALLER_VERSION: "2025.3.3"
LEVEL_ZERO_VERSION: "1.28.2"
LEVEL_ZERO_UBUNTU_VERSION: "u24.04"
continue-on-error: true
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Download & Install oneAPI
shell: bash
run: |
cd /tmp
wget https://registrationcenter-download.intel.com/akdlm/IRC_NAS/56f7923a-adb8-43f3-8b02-2b60fcac8cab/intel-deep-learning-essentials-2025.3.3.16_offline.sh -O intel-deep-learning-essentials_offline.sh
sudo bash intel-deep-learning-essentials_offline.sh -s -a --silent --eula accept
- name: Install Level Zero SDK
shell: bash
run: |
cd /tmp
wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/level-zero_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O level-zero.deb
wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/level-zero-devel_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O level-zero-devel.deb
sudo apt-get install -y ./level-zero.deb ./level-zero-devel.deb
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: sycl-ubuntu-24-${{ matrix.build }}
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
run: |
source /opt/intel/oneapi/setvars.sh
cmake -B build \
-G "Ninja" \
-DCMAKE_BUILD_TYPE=Release \
-DGGML_SYCL=ON \
-DCMAKE_C_COMPILER=icx \
-DCMAKE_CXX_COMPILER=icpx \
-DLLAMA_OPENSSL=OFF \
-DGGML_NATIVE=OFF \
-DGGML_SYCL_F16=${{ matrix.fp16 }}
time cmake --build build --config Release -j $(nproc)
windows-latest-sycl:
runs-on: windows-2022
defaults:
run:
shell: bash
env:
WINDOWS_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/b60765d1-2b85-4e85-86b6-cb0e9563a699/intel-deep-learning-essentials-2025.3.3.18_offline.exe
WINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.devel:intel.oneapi.win.dnnl:intel.oneapi.win.tbb.devel
LEVEL_ZERO_SDK_URL: https://github.com/oneapi-src/level-zero/releases/download/v1.28.2/level-zero-win-sdk-1.28.2.zip
ONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI"
ONEAPI_INSTALLER_VERSION: "2025.3.3"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Download & Install oneAPI
shell: bash
run: |
scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL
- name: Install Level Zero SDK
shell: pwsh
run: |
Invoke-WebRequest -Uri "${{ env.LEVEL_ZERO_SDK_URL }}" -OutFile "level-zero-win-sdk.zip"
Expand-Archive -Path "level-zero-win-sdk.zip" -DestinationPath "C:/level-zero-sdk" -Force
"LEVEL_ZERO_V1_SDK_PATH=C:/level-zero-sdk" | Out-File -FilePath $env:GITHUB_ENV -Append
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: sycl-windows-latest
variant: ccache
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
# TODO: add ssl support ; we will also need to modify win-build-sycl.bat to accept user-specified args
- name: Build
id: cmake_build
run: examples/sycl/win-build-sycl.bat
.github/workflows/build-virtgpu.yml
+50
View File
@@ -0,0 +1,50 @@
name: CI (virtgpu)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-virtgpu.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-virtgpu.yml',
'ggml/src/ggml-virtgpu/**'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
jobs:
ubuntu-24-virtgpu:
runs-on: ${{ 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install -y build-essential libdrm-dev pkg-config libssl-dev
- name: Build
id: cmake_build
run: |
cmake -B build \
-DGGML_VIRTGPU=ON \
-DGGML_VIRTGPU_BACKEND=ON
cmake --build build --config Release -j $(nproc)
.github/workflows/build-vulkan.yml
+134
View File
@@ -0,0 +1,134 @@
name: CI (vulkan)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-vulkan.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.comp',
'**/*.glsl'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-vulkan.yml',
'ggml/src/ggml-vulkan/**'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu-arm64:
runs-on: ubuntu-24.04-arm
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install -y gcc-14 g++-14 build-essential glslc libvulkan-dev spirv-headers libssl-dev ninja-build
echo "CC=gcc-14" >> "$GITHUB_ENV"
echo "CXX=g++-14" >> "$GITHUB_ENV"
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: vulkan-ubuntu-24.04-arm-new
variant: ccache
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Configure
id: cmake_configure
run: |
cmake -B build \
-G "Ninja" \
-DCMAKE_BUILD_TYPE=Release \
-DGGML_VULKAN=ON
- name: Build
id: cmake_build
run: |
time cmake --build build -j $(nproc)
ubuntu-llvmpipe:
runs-on: ubuntu-24.04
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
sudo add-apt-repository -y ppa:kisak/kisak-mesa
sudo apt-get update -y
sudo apt-get install -y build-essential mesa-vulkan-drivers libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libssl-dev
- name: Get latest Vulkan SDK version
id: vulkan_sdk_version
run: |
echo "VULKAN_SDK_VERSION=$(curl https://vulkan.lunarg.com/sdk/latest/linux.txt)" >> "$GITHUB_ENV"
- name: Use Vulkan SDK Cache
uses: actions/cache@v5
id: cache-sdk
with:
path: ./vulkan_sdk
key: cache-gha-vulkan-sdk-${{ env.VULKAN_SDK_VERSION }}-${{ runner.os }}
- name: Setup Vulkan SDK
if: steps.cache-sdk.outputs.cache-hit != 'true'
uses: ./.github/actions/linux-setup-vulkan
with:
path: ./vulkan_sdk
version: ${{ env.VULKAN_SDK_VERSION }}
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: vulkan-ubuntu-24.04-llvmpipe
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
run: |
source ./vulkan_sdk/setup-env.sh
cmake -B build \
-DGGML_VULKAN=ON
cmake --build build --config Release -j $(nproc)
- name: Test
id: cmake_test
run: |
cd build
export GGML_VK_VISIBLE_DEVICES=0
export GGML_VK_DISABLE_F16=1
export GGML_VK_DISABLE_COOPMAT=1
# This is using llvmpipe and runs slower than other backends
# test-backend-ops is too slow on llvmpipe, skip it
ctest -L main -E test-backend-ops --verbose --timeout 900
.github/workflows/build-webgpu.yml
+196
View File
@@ -0,0 +1,196 @@
name: CI (webgpu)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-webgpu.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.wgsl'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-webgpu.yml',
'ggml/src/ggml-webgpu/**'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
format:
runs-on: ubuntu-24.04
steps:
- name: Clone
uses: actions/checkout@v6
- name: Install clang-format 22
run: |
wget -qO- https://apt.llvm.org/llvm-snapshot.gpg.key |
sudo tee /etc/apt/trusted.gpg.d/apt.llvm.org.asc > /dev/null
sudo add-apt-repository -y \
"deb http://apt.llvm.org/noble/ llvm-toolchain-noble-22 main"
sudo apt-get update
sudo apt-get install -y clang-format-22
- name: Check formatting
run: |
find ggml/src/ggml-webgpu \
-type f \( -name '*.cpp' -o -name '*.hpp' -o -name '*.h' \) \
-print0 |
xargs -0 clang-format-22 --dry-run --Werror
macos:
runs-on: macos-latest
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: webgpu-macos-latest
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Dawn Dependency
id: dawn-depends
run: |
DAWN_VERSION="v20260317.182325"
DAWN_OWNER="google"
DAWN_REPO="dawn"
DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-macos-latest-Release"
echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
curl -L -o artifact.tar.gz \
"https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
mkdir dawn
tar -xvf artifact.tar.gz -C dawn --strip-components=1
- name: Build
id: cmake_build
run: |
export CMAKE_PREFIX_PATH=dawn
cmake -B build -G "Ninja" -DCMAKE_BUILD_TYPE=Release -DGGML_WEBGPU=ON -DGGML_METAL=OFF -DGGML_BLAS=OFF
time cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
- name: Test
id: cmake_test
run: |
cd build
ctest -L main --verbose --timeout 900
ubuntu:
runs-on: ubuntu-24.04
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: webgpu-ubuntu-24.04
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Dependencies
id: depends
run: |
sudo add-apt-repository -y ppa:kisak/kisak-mesa
sudo apt-get update -y
sudo apt-get install -y build-essential mesa-vulkan-drivers \
libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libssl-dev
- name: Dawn Dependency
id: dawn-depends
run: |
sudo apt-get install -y libxrandr-dev libxinerama-dev libxcursor-dev mesa-common-dev libx11-xcb-dev libxi-dev
DAWN_VERSION="v20260317.182325"
DAWN_OWNER="google"
DAWN_REPO="dawn"
DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-ubuntu-latest-Release"
echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
curl -L -o artifact.tar.gz \
"https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
mkdir dawn
tar -xvf artifact.tar.gz -C dawn --strip-components=1
- name: Build
id: cmake_build
run: |
export Dawn_DIR=dawn/lib64/cmake/Dawn
cmake -B build \
-DGGML_WEBGPU=ON
time cmake --build build --config Release -j $(nproc)
- name: Test
id: cmake_test
run: |
cd build
# This is using llvmpipe and runs slower than other backends
# test-backend-ops is too slow on llvmpipe, skip it
ctest -L main -E test-backend-ops --verbose --timeout 900
ubuntu-wasm:
runs-on: ubuntu-24.04-arm
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: webgpu-ubuntu-24.04-arm-wasm
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Install Emscripten
run: |
git clone https://github.com/emscripten-core/emsdk.git
cd emsdk
./emsdk install latest
./emsdk activate latest
- name: Fetch emdawnwebgpu
run: |
DAWN_TAG="v20260317.182325"
EMDAWN_PKG="emdawnwebgpu_pkg-${DAWN_TAG}.zip"
echo "Downloading ${EMDAWN_PKG}"
curl -L -o emdawn.zip \
"https://github.com/google/dawn/releases/download/${DAWN_TAG}/${EMDAWN_PKG}"
unzip emdawn.zip
- name: Build WASM WebGPU
run: |
source emsdk/emsdk_env.sh
emcmake cmake -B build-wasm \
-G "Ninja" \
-DCMAKE_BUILD_TYPE=Release \
-DGGML_WEBGPU=ON \
-DLLAMA_OPENSSL=OFF \
-DEMDAWNWEBGPU_DIR=emdawnwebgpu_pkg
time cmake --build build-wasm --config Release --target test-backend-ops -j $(nproc)
.github/workflows/check-vendor.yml
+52
View File
@@ -0,0 +1,52 @@
name: Check vendor
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'vendor/**',
'scripts/sync_vendor.py'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'vendor/**',
'scripts/sync_vendor.py'
]
jobs:
check-vendor:
runs-on: [self-hosted, fast]
steps:
- name: Checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
- name: Setup Python
uses: actions/setup-python@v6
with:
python-version: '3.x'
- name: Run vendor sync
run: |
set -euo pipefail
python3 scripts/sync_vendor.py
- name: Check for changes
run: |
set -euo pipefail
# detect modified or untracked files
changed=$(git status --porcelain --untracked-files=all || true)
if [ -n "$changed" ]; then
echo "Vendor sync modified files:"
echo "$changed" | awk '{ print $2 }' | sed '/^$/d'
echo "Failing because vendor files mismatch. Please update scripts/sync_vendor.py"
exit 1
else
echo "Vendor files are up-to-date."
fi
.github/workflows/close-issue.yml
+28
View File
@@ -0,0 +1,28 @@
name: Close inactive issues
on:
schedule:
- cron: "42 0 * * *"
# Fine-grant permission
# https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token
permissions:
issues: write
jobs:
close-issues:
runs-on: ubuntu-slim
permissions:
issues: write
pull-requests: write
steps:
- uses: actions/stale@v10
with:
exempt-issue-labels: "refactoring,help wanted,good first issue,research 🔬,bug,roadmap,security"
days-before-issue-stale: 30
days-before-issue-close: 14
stale-issue-label: "stale"
close-issue-message: "This issue was closed because it has been inactive for 14 days since being marked as stale."
days-before-pr-stale: -1
days-before-pr-close: -1
operations-per-run: 10000
repo-token: ${{ secrets.GITHUB_TOKEN }}
.github/workflows/code-style.yml
+51
View File
@@ -0,0 +1,51 @@
name: Code Style Checker
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
pull_request:
branches:
- master
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
jobs:
model-naming:
runs-on: [self-hosted, fast]
steps:
- uses: actions/checkout@v6
- name: Check model naming conventions
run: |
python3 - << 'EOF'
import re, os, sys
pairs = re.findall(
r'case\s+(LLM_ARCH_\w+)\s*:\s*\n\s+return new (llama_model_\w+)\s*\(',
open("src/llama-model.cpp").read())
errors = []
for arch, cls in pairs:
suffix = arch[len("LLM_ARCH_"):]
csuffix = cls[len("llama_model_"):]
fname = csuffix.replace("_", "-") + ".cpp"
if not re.fullmatch(r'[A-Z][A-Z0-9_]*', suffix):
errors.append(f"{arch}: suffix not upper snake case, example: LLM_ARCH_MY_MODEL")
if not re.fullmatch(r'[a-z][a-z0-9_]*', csuffix):
errors.append(f"{arch}: class suffix not lower snake case, example: llama_model_my_model")
elif suffix.lower() != csuffix:
errors.append(f"{arch}: arch/class name mismatch, expected class 'llama_model_{suffix.lower()}' but got '{cls}'")
elif not os.path.isfile(f"src/models/{fname}"):
errors.append(f"{arch}: expects model file name to be src/models/{fname}, but not found")
if errors:
print('\n'.join(f" - {e}" for e in errors)); sys.exit(1)
print(f"OK: {len(pairs)} mappings validated.")
EOF
.github/workflows/copilot-setup-steps.yml
+56
View File
@@ -0,0 +1,56 @@
name: "Copilot Setup Steps"
# Automatically run the setup steps when they are changed to allow for easy validation, and
# allow manual testing through the repository's "Actions" tab
on:
workflow_dispatch:
push:
paths:
- .github/workflows/copilot-setup-steps.yml
pull_request:
paths:
- .github/workflows/copilot-setup-steps.yml
jobs:
# The job MUST be called `copilot-setup-steps` or it will not be picked up by Copilot.
copilot-setup-steps:
runs-on: ubuntu-latest
# Set the permissions to the lowest permissions possible needed for your steps.
# Copilot will be given its own token for its operations.
permissions:
# If you want to clone the repository as part of your setup steps, for example to install dependencies, you'll need the `contents: read` permission. If you don't clone the repository in your setup steps, Copilot will do this for you automatically after the steps complete.
contents: read
# You can define any steps you want, and they will run before the agent starts.
# If you do not check out your code, Copilot will do this for you.
steps:
- name: Checkout code
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: copilot-setup-steps
evict-old-files: 1d
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install build-essential libssl-dev
# Install git-clang-format script for formatting only changed code
wget -O /tmp/git-clang-format https://raw.githubusercontent.com/llvm/llvm-project/release/18.x/clang/tools/clang-format/git-clang-format
sudo cp /tmp/git-clang-format /usr/local/bin/git-clang-format
sudo chmod +x /usr/local/bin/git-clang-format
- name: Set up Python
uses: actions/setup-python@v6
with:
python-version: '3.11'
- name: Install Python dependencies
run: |
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements/requirements-all.txt -r tools/server/tests/requirements.txt
.github/workflows/docker.yml
+529
View File
@@ -0,0 +1,529 @@
# This workflow uses actions that are not certified by GitHub.
# They are provided by a third-party and are governed by
# separate terms of service, privacy policy, and support
# documentation.
# GitHub recommends pinning actions to a commit SHA.
# To get a newer version, you will need to update the SHA.
# You can also reference a tag or branch, but the action may change without warning.
name: Publish Docker image
on:
workflow_dispatch: # allows manual triggering
inputs:
skip_s390x:
description: "Skip the s390x build target (useful for fast test runs that do not need the IBM Z runner)"
type: boolean
default: false
schedule:
# Rebuild daily rather than on every push because it is expensive
- cron: '12 4 * * *'
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
# Fine-grant permission
# https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token
permissions:
packages: write
jobs:
create_tag:
name: Create and push git tag
runs-on: ubuntu-slim
permissions:
contents: write
outputs:
source_tag: ${{ steps.srctag.outputs.name }}
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
- name: Determine source tag name
id: srctag
uses: ./.github/actions/get-tag-name
env:
BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
- name: Create and push git tag
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
git tag ${{ steps.srctag.outputs.name }} || exit 0
git push origin ${{ steps.srctag.outputs.name }} || exit 0
build_ui:
name: Build UI
needs: create_tag
uses: ./.github/workflows/ui-build.yml
with:
hf_ui_version: ${{ needs.create_tag.outputs.source_tag }}
prepare_matrices:
name: Prepare Docker matrices
runs-on: ubuntu-24.04
outputs:
build_matrix: ${{ steps.matrices.outputs.build_matrix }}
merge_matrix: ${{ steps.matrices.outputs.merge_matrix }}
steps:
- name: Generate build and merge matrices
id: matrices
shell: bash
env:
SKIP_S390X: ${{ inputs.skip_s390x || 'false' }}
run: |
set -euo pipefail
# Keep all build targets in one place and derive merge targets from it.
cat > build-matrix.json <<'JSON'
[
{ "tag": "cpu", "dockerfile": ".devops/cpu.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-24.04" },
{ "tag": "cpu", "dockerfile": ".devops/cpu.Dockerfile", "platforms": "linux/arm64", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-24.04-arm" },
{ "tag": "cpu", "dockerfile": ".devops/s390x.Dockerfile", "platforms": "linux/s390x", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-24.04-s390x", "prebuilt_ui": true },
{ "tag": "cuda cuda12", "dockerfile": ".devops/cuda.Dockerfile", "cuda_version": "12.8.1", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04" },
{ "tag": "cuda cuda12", "dockerfile": ".devops/cuda.Dockerfile", "cuda_version": "12.8.1", "platforms": "linux/arm64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04-arm" },
{ "tag": "cuda13", "dockerfile": ".devops/cuda.Dockerfile", "cuda_version": "13.3.0", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04" },
{ "tag": "cuda13", "dockerfile": ".devops/cuda.Dockerfile", "cuda_version": "13.3.0", "platforms": "linux/arm64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04-arm" },
{ "tag": "musa", "dockerfile": ".devops/musa.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04" },
{ "tag": "intel", "dockerfile": ".devops/intel.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04" },
{ "tag": "vulkan", "dockerfile": ".devops/vulkan.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-24.04" },
{ "tag": "vulkan", "dockerfile": ".devops/vulkan.Dockerfile", "platforms": "linux/arm64", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-24.04-arm" },
{ "tag": "rocm", "dockerfile": ".devops/rocm.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04" },
{ "tag": "openvino", "dockerfile": ".devops/openvino.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-24.04" }
]
JSON
if [ "${SKIP_S390X}" = "true" ]; then
jq 'map(select(.platforms != "linux/s390x"))' build-matrix.json > build-matrix.json.tmp
mv build-matrix.json.tmp build-matrix.json
fi
BUILD_MATRIX="$(jq -c . build-matrix.json)"
MERGE_MATRIX="$(jq -c '
reduce .[] as $entry ({}; .[$entry.tag] |= (
. // {
tag: $entry.tag,
arches: [],
full: false,
light: false,
server: false
}
| .full = (.full or ($entry.full // false))
| .light = (.light or ($entry.light // false))
| .server = (.server or ($entry.server // false))
| .arches += [($entry.platforms | sub("^linux/"; ""))]
))
# Backward compatibility: s390x tags are aliases of cpu for the linux/s390x platform.
| if (has("cpu") and (((.cpu.arches // []) | index("s390x")) != null)) then
. + {
s390x: {
tag: "s390x",
arches: ["s390x"],
full: .cpu.full,
light: .cpu.light,
server: .cpu.server
}
}
else
.
end
| [.[] | .arches = (.arches | unique | sort | join(" "))]
' build-matrix.json)"
echo "build_matrix=$BUILD_MATRIX" >> "$GITHUB_OUTPUT"
echo "merge_matrix=$MERGE_MATRIX" >> "$GITHUB_OUTPUT"
push_to_registry:
name: Push Docker image to Docker Registry
needs: [prepare_matrices, create_tag, build_ui]
runs-on: ${{ matrix.config.runs_on }}
strategy:
fail-fast: false
matrix:
config: ${{ fromJSON(needs.prepare_matrices.outputs.build_matrix) }}
steps:
- name: Check out the repo
id: checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
ref: ${{ needs.create_tag.outputs.source_tag }}
- name: Download prebuilt UI
if: ${{ matrix.config.prebuilt_ui == true }}
uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
with:
name: ui-build
path: tools/ui/dist
- name: Set up QEMU
if: ${{ contains(matrix.config.platforms, 'linux/amd64') }}
uses: docker/setup-qemu-action@ce360397dd3f832beb865e1373c09c0e9f86d70a # v4
with:
image: tonistiigi/binfmt:qemu-v10.2.1
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4
- name: Log in to Docker Registry
uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v4
with:
registry: ghcr.io
username: ${{ github.repository_owner }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Determine image metadata
id: meta
shell: bash
run: |
set -euo pipefail
REPO_OWNER="${GITHUB_REPOSITORY_OWNER@L}" # to lower case
REPO_NAME="${{ github.event.repository.name }}"
IMAGE_REPO="ghcr.io/${REPO_OWNER}/${REPO_NAME}"
PREFIX="${IMAGE_REPO}:"
PLATFORM="${{ matrix.config.platforms }}"
ARCH_SUFFIX="${PLATFORM#linux/}"
# list all tags possible
tags="${{ matrix.config.tag }}"
for tag in $tags; do
if [[ "$tag" == "cpu" ]]; then
TYPE=""
else
TYPE="-$tag"
fi
CACHETAG="${PREFIX}buildcache${TYPE}-${ARCH_SUFFIX}"
done
SAFE_TAGS="$(echo "$tags" | tr ' ' '_')"
echo "image_repo=$IMAGE_REPO" >> $GITHUB_OUTPUT
echo "arch_suffix=$ARCH_SUFFIX" >> $GITHUB_OUTPUT
echo "cache_output_tag=$CACHETAG" >> $GITHUB_OUTPUT
echo "digest_artifact_suffix=${SAFE_TAGS}-${ARCH_SUFFIX}" >> $GITHUB_OUTPUT
echo "cache_output_tag=$CACHETAG" # print out for debugging
env:
GITHUB_REPOSITORY_OWNER: '${{ github.repository_owner }}'
- name: Get build date
id: build_date
run: echo "date=$(date -u +"%Y-%m-%dT%H:%M:%SZ")" >> $GITHUB_OUTPUT
- name: Free Disk Space (Ubuntu)
if: ${{ matrix.config.free_disk_space == true }}
uses: ggml-org/free-disk-space@v1.3.1
with:
# this might remove tools that are actually needed,
# if set to "true" but frees about 6 GB
tool-cache: false
# all of these default to true, but feel free to set to
# "false" if necessary for your workflow
android: true
dotnet: true
haskell: true
large-packages: true
docker-images: true
swap-storage: true
- name: Build and push Full Docker image by digest
id: build_full
if: ${{ (github.event_name == 'push' || github.event_name == 'schedule' || github.event_name == 'workflow_dispatch') && matrix.config.full == true }}
uses: docker/build-push-action@d08e5c354a6adb9ed34480a06d141179aa583294 # v7
with:
context: .
platforms: ${{ matrix.config.platforms }}
outputs: type=image,name=${{ steps.meta.outputs.image_repo }},push-by-digest=true,name-canonical=true,push=true,oci-mediatypes=true
file: ${{ matrix.config.dockerfile }}
target: full
provenance: false
build-args: |
BUILD_DATE=${{ steps.build_date.outputs.date }}
APP_VERSION=${{ needs.create_tag.outputs.source_tag }}
APP_REVISION=${{ steps.checkout.outputs.commit }}
IMAGE_URL=${{ github.server_url }}/${{ github.repository }}
IMAGE_SOURCE=${{ github.server_url }}/${{ github.repository }}
${{ matrix.config.ubuntu_version && format('UBUNTU_VERSION={0}', matrix.config.ubuntu_version) || '' }}
${{ matrix.config.cuda_version && format('CUDA_VERSION={0}', matrix.config.cuda_version) || '' }}
annotations: |
manifest:org.opencontainers.image.created=${{ steps.build_date.outputs.date }}
manifest:org.opencontainers.image.version=${{ needs.create_tag.outputs.source_tag }}
manifest:org.opencontainers.image.revision=${{ steps.checkout.outputs.commit }}
manifest:org.opencontainers.image.title=llama.cpp
manifest:org.opencontainers.image.description=LLM inference in C/C++
manifest:org.opencontainers.image.url=${{ github.server_url }}/${{ github.repository }}
manifest:org.opencontainers.image.source=${{ github.server_url }}/${{ github.repository }}
# using github experimental cache
#cache-from: type=gha
#cache-to: type=gha,mode=max
# return to this if the experimental github cache is having issues
#cache-to: type=local,dest=/tmp/.buildx-cache
#cache-from: type=local,src=/tmp/.buildx-cache
# using registry cache (no storage limit)
cache-from: type=registry,ref=${{ steps.meta.outputs.cache_output_tag }}
cache-to: type=registry,ref=${{ steps.meta.outputs.cache_output_tag }},mode=max
- name: Build and push Light Docker image by digest
id: build_light
if: ${{ (github.event_name == 'push' || github.event_name == 'schedule' || github.event_name == 'workflow_dispatch') && matrix.config.light == true }}
uses: docker/build-push-action@d08e5c354a6adb9ed34480a06d141179aa583294 # v7
with:
context: .
platforms: ${{ matrix.config.platforms }}
outputs: type=image,name=${{ steps.meta.outputs.image_repo }},push-by-digest=true,name-canonical=true,push=true,oci-mediatypes=true
file: ${{ matrix.config.dockerfile }}
target: light
provenance: false
build-args: |
BUILD_DATE=${{ steps.build_date.outputs.date }}
APP_VERSION=${{ needs.create_tag.outputs.source_tag }}
APP_REVISION=${{ steps.checkout.outputs.commit }}
IMAGE_URL=${{ github.server_url }}/${{ github.repository }}
IMAGE_SOURCE=${{ github.server_url }}/${{ github.repository }}
${{ matrix.config.ubuntu_version && format('UBUNTU_VERSION={0}', matrix.config.ubuntu_version) || '' }}
${{ matrix.config.cuda_version && format('CUDA_VERSION={0}', matrix.config.cuda_version) || '' }}
annotations: |
manifest:org.opencontainers.image.created=${{ steps.build_date.outputs.date }}
manifest:org.opencontainers.image.version=${{ needs.create_tag.outputs.source_tag }}
manifest:org.opencontainers.image.revision=${{ steps.checkout.outputs.commit }}
manifest:org.opencontainers.image.title=llama.cpp
manifest:org.opencontainers.image.description=LLM inference in C/C++
manifest:org.opencontainers.image.url=${{ github.server_url }}/${{ github.repository }}
manifest:org.opencontainers.image.source=${{ github.server_url }}/${{ github.repository }}
# using github experimental cache
#cache-from: type=gha
#cache-to: type=gha,mode=max
# return to this if the experimental github cache is having issues
#cache-to: type=local,dest=/tmp/.buildx-cache
#cache-from: type=local,src=/tmp/.buildx-cache
# using registry cache (no storage limit)
cache-from: type=registry,ref=${{ steps.meta.outputs.cache_output_tag }}
cache-to: type=registry,ref=${{ steps.meta.outputs.cache_output_tag }},mode=max
- name: Build and push Server Docker image by digest
id: build_server
if: ${{ (github.event_name == 'push' || github.event_name == 'schedule' || github.event_name == 'workflow_dispatch') && matrix.config.server == true }}
uses: docker/build-push-action@d08e5c354a6adb9ed34480a06d141179aa583294 # v7
with:
context: .
platforms: ${{ matrix.config.platforms }}
outputs: type=image,name=${{ steps.meta.outputs.image_repo }},push-by-digest=true,name-canonical=true,push=true,oci-mediatypes=true
file: ${{ matrix.config.dockerfile }}
target: server
provenance: false
build-args: |
BUILD_DATE=${{ steps.build_date.outputs.date }}
APP_VERSION=${{ needs.create_tag.outputs.source_tag }}
APP_REVISION=${{ steps.checkout.outputs.commit }}
IMAGE_URL=${{ github.server_url }}/${{ github.repository }}
IMAGE_SOURCE=${{ github.server_url }}/${{ github.repository }}
${{ matrix.config.ubuntu_version && format('UBUNTU_VERSION={0}', matrix.config.ubuntu_version) || '' }}
${{ matrix.config.cuda_version && format('CUDA_VERSION={0}', matrix.config.cuda_version) || '' }}
annotations: |
manifest:org.opencontainers.image.created=${{ steps.build_date.outputs.date }}
manifest:org.opencontainers.image.version=${{ needs.create_tag.outputs.source_tag }}
manifest:org.opencontainers.image.revision=${{ steps.checkout.outputs.commit }}
manifest:org.opencontainers.image.title=llama.cpp
manifest:org.opencontainers.image.description=LLM inference in C/C++
manifest:org.opencontainers.image.url=${{ github.server_url }}/${{ github.repository }}
manifest:org.opencontainers.image.source=${{ github.server_url }}/${{ github.repository }}
# using github experimental cache
#cache-from: type=gha
#cache-to: type=gha,mode=max
# return to this if the experimental github cache is having issues
#cache-to: type=local,dest=/tmp/.buildx-cache
#cache-from: type=local,src=/tmp/.buildx-cache
# using registry cache (no storage limit)
cache-from: type=registry,ref=${{ steps.meta.outputs.cache_output_tag }}
cache-to: type=registry,ref=${{ steps.meta.outputs.cache_output_tag }},mode=max
- name: Export digest metadata
shell: bash
run: |
set -euo pipefail
TAGS="${{ matrix.config.tag }}"
ARCH_SUFFIX="${{ steps.meta.outputs.arch_suffix }}"
DIGEST_FILE="/tmp/digests/${{ steps.meta.outputs.digest_artifact_suffix }}.tsv"
mkdir -p /tmp/digests
add_digest_rows() {
local image_type="$1"
local digest="$2"
if [[ -z "$digest" ]]; then
echo "Missing digest for image_type=${image_type}" >&2
exit 1
fi
for tag in $TAGS; do
printf '%s\t%s\t%s\t%s\n' "$tag" "$ARCH_SUFFIX" "$image_type" "$digest" >> "$DIGEST_FILE"
done
}
if [[ "${{ matrix.config.full }}" == "true" ]]; then
add_digest_rows "full" "${{ steps.build_full.outputs.digest }}"
fi
if [[ "${{ matrix.config.light }}" == "true" ]]; then
add_digest_rows "light" "${{ steps.build_light.outputs.digest }}"
fi
if [[ "${{ matrix.config.server }}" == "true" ]]; then
add_digest_rows "server" "${{ steps.build_server.outputs.digest }}"
fi
- name: Upload digest metadata
uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7
with:
name: digests-${{ steps.meta.outputs.digest_artifact_suffix }}
path: /tmp/digests/${{ steps.meta.outputs.digest_artifact_suffix }}.tsv
if-no-files-found: error
merge_arch_tags:
name: Create shared tags from digests
needs: [prepare_matrices, push_to_registry, create_tag]
runs-on: ubuntu-24.04
strategy:
fail-fast: false
matrix:
config: ${{ fromJSON(needs.prepare_matrices.outputs.merge_matrix) }}
steps:
- name: Check out the repo
id: checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
- name: Get build date
id: build_date
run: echo "date=$(date -u +"%Y-%m-%dT%H:%M:%SZ")" >> $GITHUB_OUTPUT
- name: Download digest metadata
uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
with:
pattern: digests-*
path: /tmp/digests
merge-multiple: true
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4
- name: Log in to Docker Registry
uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v4
with:
registry: ghcr.io
username: ${{ github.repository_owner }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Create tags from digests
shell: bash
run: |
set -euo pipefail
REPO_OWNER="${GITHUB_REPOSITORY_OWNER@L}" # to lower case
REPO_NAME="${{ github.event.repository.name }}"
IMAGE_REPO="ghcr.io/${REPO_OWNER}/${REPO_NAME}"
PREFIX="${IMAGE_REPO}:"
SRC_TAG="${{ needs.create_tag.outputs.source_tag }}"
BUILD_DATE="${{ steps.build_date.outputs.date }}"
COMMIT_SHA="${{ steps.checkout.outputs.commit }}"
TAGS="${{ matrix.config.tag }}"
ARCHES="${{ matrix.config.arches }}"
DIGEST_GLOB="/tmp/digests/*.tsv"
if ! ls ${DIGEST_GLOB} >/dev/null 2>&1; then
echo "No digest metadata found in /tmp/digests" >&2
exit 1
fi
if [[ -z "$SRC_TAG" ]]; then
echo "Missing source tag from create_tag" >&2
exit 1
fi
find_digest() {
local tag_name="$1"
local arch="$2"
local image_type="$3"
local digest
digest="$(awk -F '\t' -v t="$tag_name" -v a="$arch" -v i="$image_type" '$1 == t && $2 == a && $3 == i { print $4; exit }' ${DIGEST_GLOB})"
# Backward compatibility: s390x tags are aliases of cpu for the linux/s390x platform.
if [[ -z "$digest" && "$tag_name" == "s390x" && "$arch" == "s390x" ]]; then
digest="$(awk -F '\t' -v t="cpu" -v a="$arch" -v i="$image_type" '$1 == t && $2 == a && $3 == i { print $4; exit }' ${DIGEST_GLOB})"
fi
if [[ -z "$digest" ]]; then
echo "Missing digest for tag=${tag_name} arch=${arch} image_type=${image_type}" >&2
exit 1
fi
echo "$digest"
}
create_manifest_tags() {
local image_type="$1"
local tag_name="$2"
local suffix="$3"
local merged_tag="${PREFIX}${image_type}${suffix}"
local merged_versioned_tag="${merged_tag}-${SRC_TAG}"
local refs=()
for arch in $ARCHES; do
local digest
digest="$(find_digest "$tag_name" "$arch" "$image_type")"
refs+=("${IMAGE_REPO}@${digest}")
done
local annotations=(
--annotation "index:org.opencontainers.image.created=${BUILD_DATE}"
--annotation "index:org.opencontainers.image.version=${SRC_TAG}"
--annotation "index:org.opencontainers.image.revision=${COMMIT_SHA}"
--annotation "index:org.opencontainers.image.title=llama.cpp"
--annotation "index:org.opencontainers.image.description=LLM inference in C/C++"
--annotation "index:org.opencontainers.image.url=${{ github.server_url }}/${{ github.repository }}"
--annotation "index:org.opencontainers.image.source=${{ github.server_url }}/${{ github.repository }}"
)
echo "Creating ${merged_tag} from ${refs[*]}"
docker buildx imagetools create "${annotations[@]}" --tag "${merged_tag}" "${refs[@]}"
echo "Creating ${merged_versioned_tag} from ${refs[*]}"
docker buildx imagetools create "${annotations[@]}" --tag "${merged_versioned_tag}" "${refs[@]}"
}
for tag in $TAGS; do
if [[ "$tag" == "cpu" ]]; then
TYPE=""
else
TYPE="-$tag"
fi
if [[ "${{ matrix.config.full }}" == "true" ]]; then
create_manifest_tags "full" "$tag" "$TYPE"
fi
if [[ "${{ matrix.config.light }}" == "true" ]]; then
create_manifest_tags "light" "$tag" "$TYPE"
fi
if [[ "${{ matrix.config.server }}" == "true" ]]; then
create_manifest_tags "server" "$tag" "$TYPE"
fi
done
env:
GITHUB_REPOSITORY_OWNER: '${{ github.repository_owner }}'
.github/workflows/editorconfig.yml
+24
View File
@@ -0,0 +1,24 @@
name: EditorConfig Checker
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
pull_request:
branches:
- master
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
jobs:
editorconfig:
runs-on: [self-hosted, fast]
steps:
- uses: actions/checkout@v6
- uses: editorconfig-checker/action-editorconfig-checker@840e866d93b8e032123c23bac69dece044d4d84c # v2.2.0
with:
version: v3.0.3
- run: editorconfig-checker
.github/workflows/gguf-publish.yml
+44
View File
@@ -0,0 +1,44 @@
# This workflow will upload a Python Package using Twine when a GGUF release is created
# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
# See `gguf-py/README.md` for how to make a release.
# This workflow uses actions that are not certified by GitHub.
# They are provided by a third-party and are governed by
# separate terms of service, privacy policy, and support
# documentation.
name: Upload Python Package
on:
workflow_dispatch:
push:
# Pattern matched against refs/tags
tags:
- 'gguf-v*' # Push events to every version tag
jobs:
deploy:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v6
- name: Set up Python
uses: actions/setup-python@v6
with:
python-version: '3.11'
pip-install: poetry==2.4.0
- name: Install dependencies
run: |
cd gguf-py
poetry install
- name: Build package
run: cd gguf-py && poetry build
- name: Publish package
uses: pypa/gh-action-pypi-publish@ed0c53931b1dc9bd32cbe73a98c7f6766f8a527e # release/v1
with:
password: ${{ secrets.PYPI_API_TOKEN }}
packages-dir: gguf-py/dist
.github/workflows/hip-quality-check.yml
+86
View File
@@ -0,0 +1,86 @@
name: HIP quality check
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/hip-quality-check.yml',
'**/*.cu',
'**/*.cuh',
'ggml/src/ggml-hip/CMakeLists.txt',
'ggml/src/ggml-cuda/vendors/hip.h',
'scripts/hip/gcn-cdna-vgpr-check.py'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/hip-quality-check.yml',
'**/*.cu',
'**/*.cuh',
'ggml/src/ggml-hip/CMakeLists.txt',
'ggml/src/ggml-cuda/vendors/hip.h',
'scripts/hip/gcn-cdna-vgpr-check.py'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu-22-hip-quality-check:
runs-on: ubuntu-22.04
container: rocm/dev-ubuntu-22.04:7.2.1
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libssl-dev python3
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: hip-quality-check-ubuntu-22.04
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build with Werror
id: cmake_build
run: |
cmake -B build -S . \
-DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \
-DGPU_TARGETS=gfx942 \
-DGGML_HIP=ON \
-DGGML_HIP_EXPORT_METRICS=Off \
-DCMAKE_HIP_FLAGS="-Werror -Wno-tautological-compare" \
-DCMAKE_BUILD_TYPE=Release
cd build
make -j $(nproc)
- name: Check for major VGPR spills
id: vgpr_check
run: |
cmake -B build -S . \
-DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \
-DGPU_TARGETS=gfx908 \
-DGGML_HIP=ON \
-DGGML_HIP_EXPORT_METRICS=On \
-DCMAKE_HIP_FLAGS="" \
-DCMAKE_BUILD_TYPE=Release
cd build
make -j $(nproc) 2>&1 | tee metrics.log | grep -v 'Rpass-analysis=kernel-resource-usage\|remark:\|^$'
python3 ../scripts/hip/gcn-cdna-vgpr-check.py metrics.log
.github/workflows/labeler.yml
+17
View File
@@ -0,0 +1,17 @@
name: "Pull Request Labeler"
on:
- pull_request_target
jobs:
labeler:
permissions:
contents: read
pull-requests: write
runs-on: ubuntu-slim
steps:
- uses: actions/checkout@v6
with:
repository: "ggml-org/llama.cpp"
- uses: actions/labeler@v6
with:
configuration-path: '.github/labeler.yml'
.github/workflows/pre-tokenizer-hashes.yml
+45
View File
@@ -0,0 +1,45 @@
name: Check Pre-Tokenizer Hashes
on:
push:
paths:
- 'conversion/base.py'
- 'convert_hf_to_gguf_update.py'
pull_request:
paths:
- 'conversion/base.py'
- 'convert_hf_to_gguf_update.py'
jobs:
pre-tokenizer-hashes:
runs-on: [self-hosted, fast]
steps:
- name: Checkout repository
uses: actions/checkout@v6
- name: Set up Python
uses: actions/setup-python@v6
with:
python-version: '3.11'
- name: Install Python dependencies
run: |
python3 -m venv .venv
.venv/bin/pip install -r requirements/requirements-convert_hf_to_gguf_update.txt
- name: Update pre-tokenizer hashes
run: |
cp conversion/base.py /tmp
.venv/bin/python convert_hf_to_gguf_update.py --check-missing
- name: Check if committed pre-tokenizer hashes matches generated version
run: |
if ! diff -q conversion/base.py /tmp/base.py; then
echo "Model pre-tokenizer hashes (in conversion/base.py) do not match generated hashes (from convert_hf_to_gguf_update.py)."
echo "To fix: run ./convert_hf_to_gguf_update.py and commit the updated conversion/base.py along with your changes"
echo "Differences found:"
diff conversion/base.py /tmp/base.py || true
exit 1
fi
echo "Model pre-tokenizer hashes are up to date."
.github/workflows/python-check-requirements.yml
+33
View File
@@ -0,0 +1,33 @@
name: Python check requirements.txt
on:
push:
paths:
- '.github/workflows/python-check-requirements.yml'
- 'scripts/check-requirements.sh'
- 'convert*.py'
- '**/requirements*.txt'
pull_request:
paths:
- '.github/workflows/python-check-requirements.yml'
- 'scripts/check-requirements.sh'
- 'convert*.py'
- '**/requirements*.txt'
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
jobs:
python-check-requirements:
runs-on: [self-hosted, CPU, fast]
name: check-requirements
steps:
- name: Check out source repository
uses: actions/checkout@v6
- name: Set up Python environment
uses: actions/setup-python@v6
with:
python-version: "3.11"
- name: Run check-requirements.sh script
run: bash scripts/check-requirements.sh
.github/workflows/python-lint.yml
+36
View File
@@ -0,0 +1,36 @@
name: flake8 Lint
on:
push:
branches:
- master
paths: [
'.github/workflows/python-lint.yml',
'**/*.py'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/python-lint.yml',
'**/*.py'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
jobs:
flake8-lint:
runs-on: [self-hosted, fast]
name: Lint
steps:
- name: Check out source repository
uses: actions/checkout@v6
- name: Set up Python environment
uses: actions/setup-python@v6
with:
python-version: "3.11"
- name: flake8 Lint
uses: py-actions/flake8@84ec6726560b6d5bd68f2a5bed83d62b52bb50ba # v2
with:
plugins: "flake8-no-print"
.github/workflows/python-type-check.yml
+43
View File
@@ -0,0 +1,43 @@
name: Python Type-Check
on:
push:
paths:
- '.github/workflows/python-type-check.yml'
- 'ty.toml'
- '**.py'
- '**/requirements*.txt'
# - 'pyrightconfig.json'
pull_request:
paths:
- '.github/workflows/python-type-check.yml'
- 'ty.toml'
- '**.py'
- '**/requirements*.txt'
# - 'pyrightconfig.json'
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
jobs:
python-type-check:
runs-on: [self-hosted, fast]
name: python type-check
steps:
- name: Check out source repository
uses: actions/checkout@v6
- name: Set up Python environment
uses: actions/setup-python@v6
with:
python-version: "3.11"
pip-install: -r requirements/requirements-all.txt ty==0.0.35
# - name: Type-check with Pyright
# uses: jakebailey/pyright-action@v2
# with:
# version: 1.1.382
# level: warning
# warnings: true
- name: Type-check with ty
run: |
ty check --output-format=github
.github/workflows/release.yml
+1727
View File
File diff suppressed because it is too large Load Diff
.github/workflows/server-sanitize.yml
+112
View File
@@ -0,0 +1,112 @@
name: Server (sanitize)
on:
workflow_dispatch: # allows manual triggering
inputs:
sha:
description: 'Commit SHA1 to build'
required: false
type: string
slow_tests:
description: 'Run slow tests'
required: true
type: boolean
push:
branches:
- master
paths: [
'.github/workflows/server-sanitize.yml',
'**/CMakeLists.txt',
'**/Makefile',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'tools/server/**.*'
]
env:
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
LLAMA_ARG_LOG_VERBOSITY: 10
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
jobs:
server:
runs-on: [self-hosted, CPU, Linux, llama-server]
strategy:
matrix:
sanitizer: [ADDRESS, UNDEFINED] # THREAD is very slow
build_type: [RelWithDebInfo]
fail-fast: false
steps:
#- name: Dependencies
# id: depends
# run: |
# sudo apt-get update
# sudo apt-get -y install \
# build-essential \
# xxd \
# git \
# cmake \
# curl \
# wget \
# language-pack-en \
# libssl-dev
- name: Clone
id: checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: Setup Node.js
uses: actions/setup-node@v6
with:
node-version: "24"
cache: "npm"
cache-dependency-path: "tools/ui/package-lock.json"
- name: Build
id: cmake_build
run: |
cmake -B build \
-DLLAMA_BUILD_BORINGSSL=ON \
-DGGML_SCHED_NO_REALLOC=ON \
-DGGML_SANITIZE_ADDRESS=${{ matrix.sanitizer == 'ADDRESS' }} \
-DGGML_SANITIZE_THREAD=${{ matrix.sanitizer == 'THREAD' }} \
-DGGML_SANITIZE_UNDEFINED=${{ matrix.sanitizer == 'UNDEFINED' }} \
-DLLAMA_SANITIZE_ADDRESS=${{ matrix.sanitizer == 'ADDRESS' }} \
-DLLAMA_SANITIZE_THREAD=${{ matrix.sanitizer == 'THREAD' }} \
-DLLAMA_SANITIZE_UNDEFINED=${{ matrix.sanitizer == 'UNDEFINED' }}
cmake --build build --config ${{ matrix.build_type }} -j $(nproc) --target llama-server
- name: Python setup
id: setup_python
uses: actions/setup-python@v6
with:
python-version: '3.11'
pip-install: -r tools/server/tests/requirements.txt
- name: Tests
id: server_integration_tests
if: ${{ (!matrix.disabled_on_pr || !github.event.pull_request) }}
run: |
cd tools/server/tests
export ${{ matrix.extra_args }}
pytest -v -x -m "not slow"
- name: Slow tests
id: server_integration_tests_slow
if: ${{ (github.event.schedule || github.event.inputs.slow_tests == 'true') && matrix.build_type == 'Release' }}
run: |
cd tools/server/tests
export ${{ matrix.extra_args }}
SLOW_TESTS=1 pytest -v -x
.github/workflows/server-self-hosted.yml
+202
View File
@@ -0,0 +1,202 @@
name: Server (self-hosted)
on:
workflow_dispatch: # allows manual triggering
inputs:
sha:
description: 'Commit SHA1 to build'
required: false
type: string
slow_tests:
description: 'Run slow tests'
required: true
type: boolean
push:
branches:
- master
paths: [
'.github/workflows/server-self-hosted.yml',
'**/CMakeLists.txt',
'**/Makefile',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.cu',
'**/*.swift',
'**/*.m',
'tools/server/**.*'
]
env:
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
LLAMA_ARG_LOG_VERBOSITY: 10
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
jobs:
server-metal:
runs-on: [self-hosted, llama-server, macOS, ARM64]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: Build
id: cmake_build
run: |
cmake -B build -DGGML_SCHED_NO_REALLOC=ON
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) --target llama-server
- name: Python setup
id: setup_python
run: |
cd tools/server/tests
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
- name: Tests (GPUx1)
id: server_integration_tests
if: ${{ !github.event.pull_request }}
run: |
cd tools/server/tests
source venv/bin/activate
pytest -v -x -m "not slow"
- name: Tests (GPUx1, backend-sampling)
id: server_integration_tests_backend_sampling
if: ${{ !github.event.pull_request }}
run: |
cd tools/server/tests
source venv/bin/activate
export LLAMA_ARG_BACKEND_SAMPLING=1
pytest -v -x -m "not slow"
- name: Tests (GPUx2)
id: server_integration_tests_gpu2
if: ${{ !github.event.pull_request }}
run: |
cd tools/server/tests
source venv/bin/activate
export GGML_METAL_DEVICES=2
pytest -v -x -m "not slow"
- name: Tests (GPUx2, backend-sampling)
id: server_integration_tests_gpu2_backend_sampling
if: ${{ !github.event.pull_request }}
run: |
cd tools/server/tests
source venv/bin/activate
export GGML_METAL_DEVICES=2 LLAMA_ARG_BACKEND_SAMPLING=1
pytest -v -x -m "not slow"
server-cuda:
runs-on: [self-hosted, llama-server, Linux, NVIDIA]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: Build
id: cmake_build
run: |
cmake -B build -DGGML_CUDA=ON -DGGML_SCHED_NO_REALLOC=ON
cmake --build build --config Release -j $(nproc) --target llama-server
- name: Python setup
id: setup_python
run: |
cd tools/server/tests
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
- name: Tests (GPUx1)
id: server_integration_tests
if: ${{ !github.event.pull_request }}
run: |
cd tools/server/tests
source venv/bin/activate
pytest -v -x -m "not slow"
- name: Tests (GPUx1, backend-sampling)
id: server_integration_tests_backend_sampling
if: ${{ !github.event.pull_request }}
run: |
cd tools/server/tests
source venv/bin/activate
export LLAMA_ARG_BACKEND_SAMPLING=1
pytest -v -x -m "not slow"
server-kleidiai:
runs-on: ah-ubuntu_22_04-c8g_8x
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: Dependencies
id: depends
run: |
set -euxo pipefail
sudo apt-get update
sudo DEBIAN_FRONTEND=noninteractive NEEDRESTART_MODE=a \
apt-get install -y \
build-essential \
libssl-dev \
python3-venv \
gpg \
wget \
time \
git-lfs
git lfs install
# install the latest cmake
sudo install -d /usr/share/keyrings
wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc \
| gpg --dearmor \
| sudo tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null
echo 'deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ jammy main' \
| sudo tee /etc/apt/sources.list.d/kitware.list
sudo apt-get update
sudo apt-get install -y cmake
- name: Build
id: cmake_build
run: |
cmake -B build -DGGML_SCHED_NO_REALLOC=ON -DGGML_CPU_KLEIDIAI=ON
cmake --build build --config Release -j $(nproc) --target llama-server
- name: Python setup
id: setup_python
run: |
cd tools/server/tests
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
- name: Tests
id: server_integration_tests
if: ${{ !github.event.pull_request }}
run: |
cd tools/server/tests
source venv/bin/activate
pytest -v -x -m "not slow"
.github/workflows/server.yml
+181
View File
@@ -0,0 +1,181 @@
name: Server
on:
workflow_dispatch: # allows manual triggering
inputs:
sha:
description: 'Commit SHA1 to build'
required: false
type: string
slow_tests:
description: 'Run slow tests'
required: true
type: boolean
push:
branches:
- master
paths: [
'.github/workflows/server.yml',
'**/CMakeLists.txt',
'**/Makefile',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.cu',
'**/*.swift',
'**/*.m',
'tools/server/**.*'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/server.yml',
'**/CMakeLists.txt',
'**/Makefile',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.cu',
'**/*.swift',
'**/*.m',
'tools/server/**.*'
]
env:
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
LLAMA_ARG_LOG_VERBOSITY: 10
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
jobs:
ubuntu:
runs-on: ubuntu-24.04-arm
steps:
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get -y install \
build-essential \
xxd \
git \
cmake \
curl \
wget \
language-pack-en \
libssl-dev
- name: Clone
id: checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: server-ubuntu-24.04-arm
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
run: |
cmake -B build \
-DGGML_SCHED_NO_REALLOC=ON
cmake --build build --config Release -j $(nproc) --target llama-server
- name: Python setup
id: setup_python
uses: actions/setup-python@v6
with:
python-version: '3.11'
pip-install: -r tools/server/tests/requirements.txt
- name: Tests
id: server_integration_tests
run: |
cd tools/server/tests
pytest -v -x -m "not slow"
- name: Slow tests
id: server_integration_tests_slow
if: ${{ github.event.schedule || github.event.inputs.slow_tests == 'true' }}
run: |
cd tools/server/tests
SLOW_TESTS=1 pytest -v -x
- name: Tests (Backend sampling)
id: server_integration_tests_backend_sampling
run: |
cd tools/server/tests
export LLAMA_ARG_BACKEND_SAMPLING=1
pytest -v -x -m "not slow"
- name: Slow tests (Backend sampling)
id: server_integration_tests_slow_backend_sampling
if: ${{ github.event.schedule || github.event.inputs.slow_tests == 'true' }}
run: |
cd tools/server/tests
export LLAMA_ARG_BACKEND_SAMPLING=1
SLOW_TESTS=1 pytest -v -x
windows:
runs-on: windows-2025
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: server-windows-2025-x64
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
shell: cmd
run: |
cmake -B build -G "Ninja Multi-Config" ^
-DCMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake ^
-DCMAKE_BUILD_TYPE=Release ^
-DLLAMA_BUILD_BORINGSSL=ON ^
-DGGML_SCHED_NO_REALLOC=ON
set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1
cmake --build build --config Release -j %NINJA_JOBS% --target llama-server
- name: Python setup
id: setup_python
uses: actions/setup-python@v6
with:
python-version: '3.11'
pip-install: -r tools/server/tests/requirements.txt
- name: Tests
id: server_integration_tests
run: |
cd tools/server/tests
$env:PYTHONIOENCODING = ":replace"
pytest -v -x -m "not slow"
- name: Slow tests
id: server_integration_tests_slow
if: ${{ github.event.schedule || github.event.inputs.slow_tests == 'true' }}
run: |
cd tools/server/tests
$env:SLOW_TESTS = "1"
pytest -v -x
.github/workflows/ui-build-self-hosted.yml
+36
View File
@@ -0,0 +1,36 @@
name: UI Build (self-hosted)
on:
workflow_call:
jobs:
build:
runs-on: [self-hosted, fast]
env:
BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
steps:
- name: Checkout code
uses: actions/checkout@v6
- name: Setup Node.js
uses: actions/setup-node@v6
with:
node-version: "24"
cache: "npm"
cache-dependency-path: "tools/ui/package-lock.json"
- name: Install dependencies
run: npm ci
working-directory: tools/ui
- name: Build application
run: npm run build
working-directory: tools/ui
- name: Upload built UI
uses: actions/upload-artifact@v6
with:
name: ui-build
path: tools/ui/dist/
retention-days: 1
.github/workflows/ui-build.yml
+48
View File
@@ -0,0 +1,48 @@
name: UI Build
on:
workflow_call:
inputs:
hf_ui_version:
description: 'Version string for version.json (e.g. 12345)'
required: false
type: string
jobs:
build:
runs-on: ubuntu-slim
env:
BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
steps:
- name: Checkout code
uses: actions/checkout@v6
- name: Setup Node.js
uses: actions/setup-node@v6
with:
node-version: "24"
cache: "npm"
cache-dependency-path: "tools/ui/package-lock.json"
- name: Install dependencies
run: npm ci
working-directory: tools/ui
- name: Build application
env:
HF_UI_VERSION: ${{ inputs.hf_ui_version || '' }}
LLAMA_BUILD_NUMBER: ${{ inputs.hf_ui_version || 'b0000' }}
run: npm run build
working-directory: tools/ui
- name: Run PWA unit tests (versioned build output)
run: npx vitest --project=unit --run tests/unit/pwa.spec.ts
working-directory: tools/ui
- name: Upload built UI
uses: actions/upload-artifact@v6
with:
name: ui-build
path: tools/ui/dist/
retention-days: 1
.github/workflows/ui-publish.yml
+75
View File
@@ -0,0 +1,75 @@
name: UI Publish
on:
workflow_call:
inputs:
version_tag:
description: 'Version tag to publish under (e.g., b1234)'
required: true
type: string
secrets:
hf_token:
description: 'Hugging Face token with write access'
required: true
jobs:
build:
name: Build static output
uses: ./.github/workflows/ui-build.yml
publish:
name: Publish UI Static Output
needs: build
runs-on: ubuntu-slim
permissions:
contents: read
env:
HF_BUCKET_NAME: ${{ vars.HF_BUCKET_UI_STATIC_OUTPUT }}
steps:
- name: Checkout code
uses: actions/checkout@v6
with:
fetch-depth: 1
- name: Download UI build artifact
uses: actions/download-artifact@v7
with:
name: ui-build
path: tools/ui/dist/
- name: Create distribution archive
run: |
tar -czf dist.tar.gz -C tools/ui/dist .
sha256sum dist.tar.gz > dist.tar.gz.sha256
mv dist.tar.gz dist.tar.gz.sha256 tools/ui/dist/
- name: Install Hugging Face Hub CLI
run: pip install -U huggingface_hub
- name: Authenticate with Hugging Face
run: hf auth login --token ${{ secrets.hf_token }}
- name: Sync built files to Hugging Face bucket (version tag)
run: |
# Upload the built files to the Hugging Face bucket under the release version
hf buckets sync tools/ui/dist hf://buckets/ggml-org/${{ env.HF_BUCKET_NAME }}/${{ inputs.version_tag }} --delete --quiet
- name: Sync built files to Hugging Face bucket (latest)
run: |
# Also upload to the 'latest' directory for fallback downloads
hf buckets sync tools/ui/dist hf://buckets/ggml-org/${{ env.HF_BUCKET_NAME }}/latest --delete --quiet
- name: Verify upload
run: |
# List the files in the bucket to verify the upload
hf buckets list hf://buckets/ggml-org/${{ env.HF_BUCKET_NAME }}/${{ inputs.version_tag }} -R -h
- name: Clean up root-level files
run: |
# Clean up any old root-level files from previous non-versioned deployments
hf buckets rm ggml-org/${{ env.HF_BUCKET_NAME }}/index.html --yes 2>/dev/null || true
hf buckets rm ggml-org/${{ env.HF_BUCKET_NAME }}/bundle.js --yes 2>/dev/null || true
hf buckets rm ggml-org/${{ env.HF_BUCKET_NAME }}/bundle.css --yes 2>/dev/null || true
.github/workflows/ui-self-hosted.yml
+125
View File
@@ -0,0 +1,125 @@
name: UI (self-hosted)
# these are the same as ui.yml, but with self-hosted runners
# the jobs are lighter because they don't need to install Node.js or Playwright browsers
# the runner has pre-installed Playwright browsers for @playwright/test (1.56.1) at /ms-playwright/
on:
workflow_dispatch:
inputs:
sha:
description: 'Commit SHA1 to build'
required: false
type: string
push:
branches:
- master
paths: [
'.github/workflows/ui-self-hosted.yml',
'.github/workflows/ui-build-self-hosted.yml',
'tools/ui/**.*',
'tools/server/tests/**.*'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/ui-self-hosted.yml',
'.github/workflows/ui-build-self-hosted.yml',
'tools/ui/**.*',
'tools/server/tests/**.*'
]
env:
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
LLAMA_ARG_LOG_VERBOSITY: 10
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
jobs:
ui-build:
name: Build static output
uses: ./.github/workflows/ui-build-self-hosted.yml
ui-checks:
name: Checks
needs: ui-build
runs-on: [self-hosted, PLAYWRIGHT]
continue-on-error: true
steps:
- name: Checkout code
uses: actions/checkout@v6
with:
fetch-depth: 0
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: Install dependencies
id: setup
run: npm ci
working-directory: tools/ui
- name: Download built UI artifacts
uses: actions/download-artifact@v6
with:
name: ui-build
path: tools/ui/dist/
- name: Run type checking
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npm run check
working-directory: tools/ui
- name: Run linting
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npm run lint
working-directory: tools/ui
- name: Run Client tests
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npm run test:client
working-directory: tools/ui
- name: Run Unit tests
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npm run test:unit
working-directory: tools/ui
e2e-tests:
name: E2E Tests
needs: ui-build
runs-on: [self-hosted, PLAYWRIGHT]
steps:
- name: Checkout code
uses: actions/checkout@v6
with:
fetch-depth: 0
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: Install dependencies
id: setup
run: npm ci
working-directory: tools/ui
- name: Download built UI artifacts
uses: actions/download-artifact@v6
with:
name: ui-build
path: tools/ui/dist/
- name: Build Storybook
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npm run build-storybook
working-directory: tools/ui
- name: Run UI tests
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npm run test:ui -- --testTimeout=60000
working-directory: tools/ui
- name: Run E2E tests
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npm run test:e2e
working-directory: tools/ui
.github/workflows/ui.yml
+151
View File
@@ -0,0 +1,151 @@
name: UI
on:
workflow_dispatch:
inputs:
sha:
description: 'Commit SHA1 to build'
required: false
type: string
push:
branches:
- master
paths: [
'.github/workflows/ui.yml',
'.github/workflows/ui-build.yml',
'tools/ui/**.*',
'tools/server/tests/**.*'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/ui.yml',
'.github/workflows/ui-build.yml',
'tools/ui/**.*',
'tools/server/tests/**.*'
]
env:
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
LLAMA_ARG_LOG_VERBOSITY: 10
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
jobs:
ui-build:
name: Build static output
uses: ./.github/workflows/ui-build.yml
ui-checks:
name: Checks
needs: ui-build
runs-on: ubuntu-24.04
continue-on-error: true
steps:
- name: Checkout code
uses: actions/checkout@v6
with:
fetch-depth: 0
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: Setup Node.js
id: node
uses: actions/setup-node@v6
with:
node-version: "24"
cache: "npm"
cache-dependency-path: "tools/ui/package-lock.json"
- name: Download built UI artifacts
uses: actions/download-artifact@v6
with:
name: ui-build
path: tools/ui/dist/
- name: Install dependencies
id: setup
if: ${{ steps.node.conclusion == 'success' }}
run: npm ci
working-directory: tools/ui
- name: Run type checking
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npm run check
working-directory: tools/ui
- name: Run linting
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npm run lint
working-directory: tools/ui
- name: Install Playwright browsers
id: playwright
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npx playwright install --with-deps
working-directory: tools/ui
- name: Run Client tests
if: ${{ always() && steps.playwright.conclusion == 'success' }}
run: npm run test:client
working-directory: tools/ui
- name: Run Unit tests (uses pre-built dist/ from ui-build)
if: ${{ always() && steps.playwright.conclusion == 'success' }}
run: npm run test:unit
working-directory: tools/ui
e2e-tests:
name: E2E Tests
needs: ui-build
runs-on: ubuntu-24.04
steps:
- name: Checkout code
uses: actions/checkout@v6
with:
fetch-depth: 0
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: Setup Node.js
id: node
uses: actions/setup-node@v6
with:
node-version: "24"
cache: "npm"
cache-dependency-path: "tools/ui/package-lock.json"
- name: Install dependencies
id: setup
if: ${{ steps.node.conclusion == 'success' }}
run: npm ci
working-directory: tools/ui
- name: Download built UI artifacts (reuses ui-build)
uses: actions/download-artifact@v6
with:
name: ui-build
path: tools/ui/dist/
- name: Install Playwright browsers
id: playwright
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npx playwright install --with-deps
working-directory: tools/ui
- name: Build Storybook
if: ${{ always() && steps.playwright.conclusion == 'success' }}
run: npm run build-storybook
working-directory: tools/ui
- name: Run UI tests
if: ${{ always() && steps.playwright.conclusion == 'success' }}
run: npm run test:ui -- --testTimeout=60000
working-directory: tools/ui
- name: Run E2E tests (uses pre-built dist/ from ui-build)
if: ${{ always() && steps.playwright.conclusion == 'success' }}
run: npm run test:e2e
working-directory: tools/ui
.github/workflows/update-ops-docs.yml
+44
View File
@@ -0,0 +1,44 @@
name: Update Operations Documentation
on:
push:
paths:
- '.github/workflows/update-ops-docs.yml'
- 'docs/ops.md'
- 'docs/ops/**'
- 'scripts/create_ops_docs.py'
pull_request:
paths:
- '.github/workflows/update-ops-docs.yml'
- 'docs/ops.md'
- 'docs/ops/**'
- 'scripts/create_ops_docs.py'
jobs:
update-ops-docs:
runs-on: [self-hosted, fast, ARM64]
steps:
- name: Checkout repository
uses: actions/checkout@v6
- name: Set up Python
uses: actions/setup-python@v6
with:
python-version: '3.x'
- name: Generate operations documentation to temporary file
run: |
mkdir -p /tmp/ops_check
./scripts/create_ops_docs.py /tmp/ops_check/ops.md
- name: Check if docs/ops.md matches generated version
run: |
if ! diff -q docs/ops.md /tmp/ops_check/ops.md; then
echo "Operations documentation (docs/ops.md) is not up to date with the backend CSV files."
echo "To fix: run ./scripts/create_ops_docs.py and commit the updated docs/ops.md along with your changes"
echo "Differences found:"
diff docs/ops.md /tmp/ops_check/ops.md || true
exit 1
fi
echo "Operations documentation is up to date."
.github/workflows/winget.yml
+44
View File
@@ -0,0 +1,44 @@
name: Update Winget Package
on:
workflow_dispatch: # allows manual triggering
schedule:
- cron: '28 5 * * *' # Update every day at 5:28 UTC
jobs:
update:
name: Update Winget Package
runs-on: ubuntu-latest
if: github.repository_owner == 'ggml-org'
steps:
- name: Install cargo binstall
uses: cargo-bins/cargo-binstall@268643a6b5ea099f5718ee5cd3ff7dc89a5eb49b
- name: Install komac
run: |
cargo binstall komac@2.16.0 -y
- name: Find latest release
id: find_latest_release
uses: actions/github-script@v8
with:
script: |
const { data: releases } = await github.rest.repos.listReleases({
owner: context.repo.owner,
repo: context.repo.repo,
});
const { tag_name: version, assets: assets } = releases.find(({assets}) => assets.find(asset => asset.name.includes('win-vulkan')));
const { browser_download_url: asset_url } = assets.find(asset => asset.name.includes('win-vulkan'));
console.log("Latest release:", version);
core.setOutput('VERSION', version);
core.setOutput('ASSETURL', asset_url);
- name: Update manifest
run: |
echo "Updating manifest..."
komac update --version ${{ steps.find_latest_release.outputs.VERSION }} \
--urls "${{ steps.find_latest_release.outputs.ASSETURL }}" \
--token ${{ secrets.WINGET_GITHUB_TOKEN }} \
--submit \
ggml.llamacpp
.gitignore
+155
View File
@@ -0,0 +1,155 @@
# Extensions
*.a
*.bat
*.bin
*.d
*.dll
*.dot
*.etag
*.exe
*.gcda
*.gcno
*.gcov
*.gguf
*.gguf.json
*.lastModified
*.log
*.metallib
*.o
*.so
*.swp
*.tmp
*.DS_Store
# IDE / OS
/.cache/
/.ccls-cache/
/.direnv/
/.envrc
/.idea/
/.swiftpm
/.vs/
/.vscode/
/nppBackup
# Coverage
/gcovr-report/
/lcov-report/
# Build Artifacts
/tags
/.build/
/build*
/release
/debug
/libllama.so
/llama-*
/vulkan-shaders-gen
/rpc-server
/out/
/tmp/
/autogen-*.md
/common/build-info.cpp
# Deprecated
/main
/server
# CI
!/.github/workflows/*.yml
# Models
/models/*
/models-mnt
!/models/.editorconfig
!/models/ggml-vocab-*.gguf*
!/models/templates
# Zig
/zig-out/
/zig-cache/
# Examples
/examples/jeopardy/results.txt
/tools/server/*.css.hpp
/tools/server/*.html.hpp
/tools/server/*.js.hpp
/tools/server/*.mjs.hpp
/tools/server/*.gz.hpp
!/build_64.sh
!/examples/*.bat
!/examples/*/*.kts
!/examples/*/*/*.kts
!/examples/sycl/*.bat
!/examples/sycl/*.sh
# Python
/.venv
__pycache__/
*/poetry.lock
poetry.toml
poetry.lock
uv.lock
# Nix
flake.lock
/result
# Test binaries
/tests/test-backend-ops
/tests/test-double-float
/tests/test-grad0
/tests/test-grammar-parser
/tests/test-llama-grammar
/tests/test-opt
/tests/test-quantize-fns
/tests/test-quantize-perf
/tests/test-rope
/tests/test-sampling
/tests/test-tokenizer-0
/tests/test-tokenizer-1-bpe
/tests/test-tokenizer-1-spm
# Scripts
!/scripts/install-oneapi.bat
# Generated by scripts
/hellaswag_val_full.txt
/winogrande-debiased-eval.csv
/wikitext-2-raw/
# Test models for lora adapters
/lora-tests
# Local scripts
/run-vim.sh
/run-chat.sh
/run-spec.sh
/.ccache/
# IDE
/*.code-workspace
/.windsurf/
# emscripten
a.out.*
# AGENTS
AGENTS.local.md
.pi/SYSTEM.md

Some files were not shown because too many files have changed in this diff Show More