Files
wehub-resource-sync 94057c3d3e
PR Test (NPU) / check-changes (push) Has been cancelled
PR Test (NPU) / pr-gate (push) Has been cancelled
PR Test (NPU) / set-image-config (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-4-npu-a3 (push) Has been cancelled
PR Test (NPU) / stage-b-test-16-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-1-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-2-npu-a3 (push) Has been cancelled
PR Test (Arm64) / pr-gate (push) Has been cancelled
PR Test (Arm64) / check-changes (push) Has been cancelled
PR Test (Arm64) / build-test (push) Has been cancelled
PR Test (sgl-router) / gate (push) Has been cancelled
PR Test (sgl-router) / tier-1 — lint (push) Has been cancelled
PR Test (sgl-router) / tier-2 — build + test (push) Has been cancelled
PR Test (sgl-router) / tier-3 — docker (placeholder) (push) Has been cancelled
PR Test (sgl-router) / tier-3 — k8s integration (push) Has been cancelled
PR Test (sgl-router) / tier-3 — e2e (push) Has been cancelled
PR Test (sgl-router) / finish (push) Has been cancelled
PR Test (NPU) / single-node-poc (map[name:qwen3_6_27b_w8a8_1p_in64k_out1k_50ms runner:linux-aarch64-a3-2 test_case:test/registered/ascend/performance/qwen3_6_27b/test_npu_qwen3_6_27b_w8a8_1p_in64k_out1k_50ms.py test_type:perf]) (push) Has been cancelled
PR Test (NPU) / pr-test-npu-finish (push) Has been cancelled
PR Test (Xeon) / pr-gate (push) Has been cancelled
PR Test (Xeon) / check-changes (push) Has been cancelled
PR Test (Xeon) / build-test (, xeon-gnr, base-b-test-cpu) (push) Has been cancelled
PR Test (XPU) / check-changes (push) Has been cancelled
PR Test (XPU) / pr-gate (push) Has been cancelled
PR Test (XPU) / stage-a-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / wait-for-stage-a (push) Has been cancelled
PR Test (XPU) / stage-b-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / finish (push) Has been cancelled
CI Model Inventory / build-inventory (push) Has been cancelled
Lint / lint (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Compilation Check (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Manual Policy (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Request Processing (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Summary (push) Has been cancelled
PR Test (SMG) / build-wheel (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on windows (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (x86_64 - auto) (push) Has been cancelled
PR Test (SMG) / python-unit-tests (push) Has been cancelled
PR Test (SMG) / unit-tests (push) Has been cancelled
PR Test (SMG) / benchmarks (push) Has been cancelled
PR Test (SMG) / chat-completions (push) Has been cancelled
PR Test (SMG) / chat-completions-4gpu (push) Has been cancelled
PR Test (SMG) / e2e (push) Has been cancelled
PR Test (SMG) / docker-build-test (push) Has been cancelled
PR Test (SMG) / k8s-integration (push) Has been cancelled
PR Test (SMG) / finish (push) Has been cancelled
PR Test (SMG) / summarize-benchmarks (push) Has been cancelled
Release SGLang Model Gateway Docker Image / publish (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Build SDist (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Upload to PyPI (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (aarch64, 12.9, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (x86_64, 12.9, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu129 (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (aarch64, 13.0, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (x86_64, 13.0, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu130 (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 700) (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 720) (push) Has been cancelled
Release SGLang Kernels / release-rocm700 (push) Has been cancelled
Release SGLang Kernels / release-rocm720 (push) Has been cancelled
Release SGLang Kernels / build-musa43 (43, 3.10) (push) Has been cancelled
Release SGLang Kernels / release-musa43 (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:38:16 +08:00

94 lines
2.5 KiB
Bash
Executable File

#!/bin/bash
set -euo pipefail
# Detect GPU family from hostname (e.g., linux-mi35x-gpu-1-xxxxx-runner-zzzzz)
HOSTNAME_VALUE=$(hostname)
GPU_FAMILY=""
# Host names look like: linux-mi35x-gpu-1-xxxxx-runner-zzzzz
if [[ "${HOSTNAME_VALUE}" =~ ^linux-(mi[0-9]+[a-z]*)-gpu-[0-9]+ ]]; then
GPU_FAMILY="${BASH_REMATCH[1]}"
echo "Detected GPU family from hostname: ${GPU_FAMILY}"
else
echo "Warning: could not parse GPU family from '${HOSTNAME_VALUE}'"
fi
WORKDIR="/sglang-checkout/test"
declare -A ENV_MAP=(
[SGLANG_IS_IN_CI_AMD]=1
[SGLANG_IS_IN_CI]=1
# Disabled on AMD: the async-assert probes (#27461) fire torch._assert_async in
# the MXFP4 EAGLE-MTP decode path and abort the queue with an HSA hardware
# exception.
[SGLANG_ENABLE_ASYNC_ASSERT]=0
[SGLANG_USE_AITER]=1
)
# Conditionally add GPU_ARCHS only for mi35x
if [[ "${GPU_FAMILY}" == "mi35x" ]]; then
ENV_MAP[GPU_ARCHS]="gfx950"
fi
# Parse -w/--workdir and -e ENV=VAL
while [[ $# -gt 0 ]]; do
case "$1" in
-w|--workdir)
WORKDIR="$2"
shift 2
;;
-e)
IFS="=" read -r key val <<< "$2"
ENV_MAP["$key"]="$val"
shift 2
;;
--)
shift
break
;;
*)
break
;;
esac
done
# Build final ENV_ARGS
ENV_ARGS=()
for key in "${!ENV_MAP[@]}"; do
ENV_ARGS+=("-e" "$key=${ENV_MAP[$key]}")
done
# Run docker exec with retry logic for HuggingFace network/download issues
# When HF model downloads fail due to network timeouts or rate limits,
# retrying with HF_HUB_OFFLINE=1 uses cached models from previous downloads.
#
# First attempt: normal mode (allows HF downloads)
if docker exec \
-w "$WORKDIR" \
"${ENV_ARGS[@]}" \
ci_sglang "$@"; then
exit 0
else
FIRST_EXIT_CODE=$?
fi
echo "First attempt failed with exit code $FIRST_EXIT_CODE"
# Skip retry for test failures that won't be fixed by offline mode:
# - Exit 1: Test assertion failures (accuracy below threshold)
# - Exit 137 (128+9): Process killed by OOM
# - Exit 255: Test suite completed with test errors
# Only retry for other exit codes (e.g., network timeouts, HF download failures)
if [[ "$FIRST_EXIT_CODE" -eq 1 || "$FIRST_EXIT_CODE" -eq 137 || "$FIRST_EXIT_CODE" -eq 255 ]]; then
echo "Exit code $FIRST_EXIT_CODE indicates test failure (not network issue), not retrying"
exit $FIRST_EXIT_CODE
fi
echo "Retrying with HF_HUB_OFFLINE=1 (offline mode to use cached models)..."
# Second attempt: force HF offline mode to avoid network timeouts
docker exec \
-w "$WORKDIR" \
"${ENV_ARGS[@]}" \
-e HF_HUB_OFFLINE=1 \
ci_sglang "$@"