Skip to content

[HiCache] feat: Add detailed cache hit breakdown for HiCache in sglext and Prometheus metrics #47482

[HiCache] feat: Add detailed cache hit breakdown for HiCache in sglext and Prometheus metrics

[HiCache] feat: Add detailed cache hit breakdown for HiCache in sglext and Prometheus metrics #47482

Workflow file for this run

name: PR Test (Xeon)
on:
push:
branches: [ main ]
pull_request:
branches: [ main ]
workflow_dispatch:
workflow_call:
inputs:
ref:
description: 'Git ref (branch, tag, or SHA) to test. If not provided, uses the default branch.'
required: false
type: string
default: ''
run_all_tests:
description: "Run all tests (for releasing or testing purpose)"
required: false
type: boolean
default: false
concurrency:
group: pr-test-xeon-${{ inputs.ref || github.ref }}
cancel-in-progress: false
jobs:
# ==================== Check Changes ==================== #
check-changes:
runs-on: ubuntu-latest
outputs:
main_package: ${{ steps.filter.outputs.main_package || steps.run-mode.outputs.run_all_tests}}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.ref || github.ref }}
- name: Determine run mode
id: run-mode
run: |
# Run all tests for workflow_call (when ref input is provided)
# Note: github.event_name is inherited from caller, so we detect workflow_call by checking inputs.ref
if [[ "${{ inputs.run_all_tests }}" == "true" ]]; then
echo "run_all_tests=true" >> $GITHUB_OUTPUT
echo "Run mode: ALL TESTS (run_all_tests=${{ inputs.run_all_tests }})"
else
echo "run_all_tests=false" >> $GITHUB_OUTPUT
echo "Run mode: FILTERED (triggered by ${{ github.event_name }})"
fi
- name: Detect file changes
id: filter
uses: dorny/paths-filter@v3
if: steps.run-mode.outputs.run_all_tests != 'true'
with:
filters: |
main_package:
- "python/sglang/!(multimodal_gen)/**"
- "python/pyproject_cpu.toml"
- "test/**"
# Only trigger on CPU-specific sgl-kernel changes
- "sgl-kernel/pyproject_cpu.toml"
- "sgl-kernel/csrc/cpu/**"
- "sgl-kernel/python/**"
- "sgl-kernel/include/**"
- "sgl-kernel/tests/**"
- ".github/workflows/pr-test-xeon.yml"
- "docker/xeon.Dockerfile"
# ==================== PR Gate ==================== #
pr-gate:
needs: check-changes
if: needs.check-changes.outputs.main_package == 'true'
uses: ./.github/workflows/pr-gate.yml
secrets: inherit
build-test:
needs: [check-changes, pr-gate]
if: needs.check-changes.outputs.main_package == 'true'
runs-on: xeon-gnr
env:
HF_HOME: /home/sdp/.cache/huggingface
strategy:
matrix:
build_type: ['all']
steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
ref: ${{ inputs.ref || github.ref }}
- name: Build and Push
run: |
version=$(cat python/sglang/version.py | cut -d'"' -f2)
tag=v${version}-xeon
PR_REPO=${{ github.event.pull_request.head.repo.clone_url }}
PR_HEAD_REF=${{ github.head_ref }}
docker build \
${PR_REPO:+--build-arg SGLANG_REPO=$PR_REPO} \
${PR_HEAD_REF:+--build-arg VER_SGLANG=$PR_HEAD_REF} \
. -f docker/xeon.Dockerfile -t sglang_xeon --no-cache
- name: Run container
run: |
docker run -dt \
-v ${{ github.workspace }}:/sglang-checkout/ --ipc=host \
-v ${HF_HOME}:/root/.cache/huggingface \
--name ci_sglang_xeon \
sglang_xeon
- name: Check AMX support
id: check_amx
timeout-minutes: 5
run: |
docker exec -w /sglang-checkout/ ci_sglang_xeon \
bash -c "source /opt/.venv/bin/activate && python3 -c 'import torch; import sgl_kernel; assert torch._C._cpu._is_amx_tile_supported(); assert hasattr(torch.ops.sgl_kernel, \"convert_weight_packed\"); '"
- name: Run unit tests
timeout-minutes: 36
run: |
docker exec -w /sglang-checkout/ ci_sglang_xeon \
bash -c "source /opt/.venv/bin/activate && cd ./test/srt && python3 run_suite.py --suite per-commit-cpu --timeout-per-file 1500"
- name: Change permission
timeout-minutes: 2
run: |
docker exec -u root ci_sglang_xeon bash -c "
rm -rf /tmp/ci-home &&
chown -R $(id -u):$(id -g) /sglang-checkout/ 2>/dev/null || true
"
- name: Cleanup container
if: always()
run: |
docker rm -f ci_sglang_xeon || true