[XPU] Add registry mechanism for XPU CI tests (#25405)
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
This commit is contained in:
vikram singh shekhawat
co-authored by
Ma Mingfei
Ma Mingfei
parent
87c3171aaa
commit
737c6cd6d1
@@ -68,7 +68,8 @@ jobs:
|
||||
uses: ./.github/workflows/pr-gate.yml
|
||||
secrets: inherit
|
||||
|
||||
build-and-test:
|
||||
# ==================== Stage A ==================== #
|
||||
stage-a-test-1-gpu-xpu:
|
||||
needs: [check-changes, pr-gate]
|
||||
if: needs.check-changes.outputs.main_package == 'true'
|
||||
runs-on: intel-bmg
|
||||
@@ -108,16 +109,80 @@ jobs:
|
||||
run: |
|
||||
cid="${{ steps.start_container.outputs.container_id }}"
|
||||
docker exec "$cid" /home/sdp/miniforge3/envs/py3.12/bin/python3 -m pip install --upgrade pip
|
||||
docker exec "$cid" /home/sdp/miniforge3/envs/py3.12/bin/python3 -m pip install pytest expecttest ray huggingface_hub
|
||||
docker exec "$cid" /home/sdp/miniforge3/envs/py3.12/bin/python3 -m pip install pytest expecttest ray huggingface_hub tabulate
|
||||
docker exec "$cid" /home/sdp/miniforge3/envs/py3.12/bin/python3 -m pip uninstall -y flashinfer-python
|
||||
docker exec "$cid" /bin/bash -c '/home/sdp/miniforge3/envs/py3.12/bin/hf auth login --token ${HF_TOKEN} '
|
||||
|
||||
- name: Run stage-a tests
|
||||
timeout-minutes: 30
|
||||
run: |
|
||||
cid="${{ steps.start_container.outputs.container_id }}"
|
||||
docker exec "$cid" bash -c "source /home/sdp/miniforge3/bin/activate && conda activate py3.12 && cd /home/sdp/sglang/test && python3 run_suite.py --hw xpu --suite stage-a-test-1-gpu-xpu"
|
||||
|
||||
- name: Run E2E Bfloat16 tests
|
||||
- name: Cleanup container
|
||||
if: always()
|
||||
run: |
|
||||
cid="${{ steps.start_container.outputs.container_id }}"
|
||||
docker rm -f "$cid" || true
|
||||
|
||||
# ==================== Wait for Stage A ==================== #
|
||||
wait-for-stage-a:
|
||||
needs: [stage-a-test-1-gpu-xpu]
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- run: echo "stage-a passed"
|
||||
|
||||
# ==================== Stage B ==================== #
|
||||
stage-b-test-1-gpu-xpu:
|
||||
needs: [check-changes, pr-gate, wait-for-stage-a]
|
||||
if: needs.check-changes.outputs.main_package == 'true'
|
||||
runs-on: intel-bmg
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
ref: ${{ inputs.ref || github.ref }}
|
||||
|
||||
- name: Build Docker image
|
||||
run: |
|
||||
PR_REPO=${{ github.event.pull_request.head.repo.clone_url }}
|
||||
PR_HEAD_REF=${{ github.head_ref }}
|
||||
docker build \
|
||||
${PR_REPO:+--build-arg SG_LANG_REPO=$PR_REPO} \
|
||||
${PR_HEAD_REF:+--build-arg SG_LANG_BRANCH=$PR_HEAD_REF} \
|
||||
--no-cache --progress=plain -f docker/xpu.Dockerfile -t xpu_sglang_main:bmg .
|
||||
|
||||
- name: Run container
|
||||
id: start_container
|
||||
run: |
|
||||
container_id=$(docker run -dt \
|
||||
--group-add 992 \
|
||||
--group-add $(getent group video | cut -d: -f3) \
|
||||
--group-add $(getent group render | cut -d: -f3) \
|
||||
-v $HOME/.cache/huggingface:/root/.cache/huggingface \
|
||||
--device /dev/dri \
|
||||
-v /dev/dri/by-path:/dev/dri/by-path \
|
||||
-e HF_TOKEN="$(cat ~/huggingface_token.txt)" \
|
||||
xpu_sglang_main:bmg)
|
||||
echo "Started container: $container_id"
|
||||
echo "container_id=$container_id" >> "$GITHUB_OUTPUT"
|
||||
|
||||
- name: Install Dependency
|
||||
timeout-minutes: 20
|
||||
run: |
|
||||
cid="${{ steps.start_container.outputs.container_id }}"
|
||||
docker exec "$cid" bash -c "source /home/sdp/miniforge3/bin/activate && conda activate py3.12 && cd /home/sdp/sglang/test/srt && python3 run_suite.py --suite per-commit-xpu"
|
||||
docker exec "$cid" /home/sdp/miniforge3/envs/py3.12/bin/python3 -m pip install --upgrade pip
|
||||
docker exec "$cid" /home/sdp/miniforge3/envs/py3.12/bin/python3 -m pip install pytest expecttest ray huggingface_hub tabulate
|
||||
docker exec "$cid" /home/sdp/miniforge3/envs/py3.12/bin/python3 -m pip uninstall -y flashinfer-python
|
||||
docker exec "$cid" /bin/bash -c '/home/sdp/miniforge3/envs/py3.12/bin/hf auth login --token ${HF_TOKEN} '
|
||||
|
||||
- name: Run stage-b tests
|
||||
timeout-minutes: 60
|
||||
run: |
|
||||
cid="${{ steps.start_container.outputs.container_id }}"
|
||||
docker exec "$cid" bash -c "source /home/sdp/miniforge3/bin/activate && conda activate py3.12 && cd /home/sdp/sglang/test && python3 run_suite.py --hw xpu --suite stage-b-test-1-gpu-xpu"
|
||||
|
||||
- name: Cleanup container
|
||||
if: always()
|
||||
run: |
|
||||
@@ -126,15 +191,20 @@ jobs:
|
||||
|
||||
finish:
|
||||
if: always()
|
||||
needs: [build-and-test, pr-gate]
|
||||
needs: [stage-a-test-1-gpu-xpu, stage-b-test-1-gpu-xpu, pr-gate]
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Check job status
|
||||
run: |
|
||||
result="${{ needs.build-and-test.result }}"
|
||||
if [ "$result" != "success" ] && [ "$result" != "skipped" ]; then
|
||||
echo "Job failed with result: $result"
|
||||
stage_a="${{ needs.stage-a-test-1-gpu-xpu.result }}"
|
||||
stage_b="${{ needs.stage-b-test-1-gpu-xpu.result }}"
|
||||
if [ "$stage_a" != "success" ] && [ "$stage_a" != "skipped" ]; then
|
||||
echo "stage-a failed with result: $stage_a"
|
||||
exit 1
|
||||
fi
|
||||
echo "All jobs completed successfully (result: $result)"
|
||||
if [ "$stage_b" != "success" ] && [ "$stage_b" != "skipped" ]; then
|
||||
echo "stage-b failed with result: $stage_b"
|
||||
exit 1
|
||||
fi
|
||||
echo "All jobs completed successfully"
|
||||
exit 0
|
||||
|
||||
Reference in New Issue
Block a user