Files
sglang/.github/workflows/nightly-test-nvidia.yml

293 lines
8.9 KiB
YAML

name: Nightly Test (Nvidia)
on:
schedule:
- cron: '0 0 * * *'
push:
branches:
- main
paths:
- "python/sglang/version.py"
workflow_dispatch:
concurrency:
group: nightly-test-nvidia-${{ github.ref }}
cancel-in-progress: true
jobs:
# General tests - 1 GPU
nightly-test-general-1-gpu-runner:
if: github.repository == 'sgl-project/sglang'
runs-on: 1-gpu-runner
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Install dependencies
run: |
bash scripts/ci/ci_install_dependency.sh
- name: Run test
timeout-minutes: 60
run: |
cd test/srt
python3 run_suite.py --suite nightly-1-gpu --continue-on-error
# General tests - 4 GPU H100
nightly-test-general-4-gpu-h100:
if: github.repository == 'sgl-project/sglang'
runs-on: 4-gpu-h100
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Install dependencies
run: |
bash scripts/ci/ci_install_dependency.sh
- name: Run test
timeout-minutes: 30
run: |
cd test/srt
python3 run_suite.py --suite nightly-4-gpu --continue-on-error
# General tests - 8 GPU H200
nightly-test-general-8-gpu-h200:
if: github.repository == 'sgl-project/sglang'
runs-on: 8-gpu-h200
env:
RUNNER_LABELS: 8-gpu-h200
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Install dependencies
run: |
bash scripts/ci/ci_install_dependency.sh
- name: Run test
timeout-minutes: 30
env:
GPU_CONFIG: "8-gpu-h200"
run: |
cd test/srt
python3 run_suite.py --suite nightly-8-gpu-h200 --continue-on-error
# General tests - 8 GPU H20
nightly-test-general-8-gpu-h20:
if: github.repository == 'sgl-project/sglang'
runs-on: 8-gpu-h20
env:
SGLANG_CI_RDMA_ALL_DEVICES: "mlx5_1,mlx5_2,mlx5_3,mlx5_4"
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Install dependencies
run: |
bash scripts/ci/ci_install_dependency.sh
- name: Run test
timeout-minutes: 30
env:
GPU_CONFIG: "8-gpu-h20"
run: |
cd test/srt
python3 run_suite.py --suite nightly-8-gpu-h20 --continue-on-error
# Text model accuracy tests
nightly-test-text-accuracy-2-gpu-runner:
if: github.repository == 'sgl-project/sglang'
runs-on: 2-gpu-runner
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Install dependencies
run: |
bash scripts/ci/ci_install_dependency.sh
- name: Run eval test for text models
timeout-minutes: 120
run: |
cd test/srt
python3 nightly/test_text_models_gsm8k_eval.py
# Text model performance tests
nightly-test-text-perf-2-gpu-runner:
if: github.repository == 'sgl-project/sglang'
runs-on: 2-gpu-runner
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Install dependencies
run: |
bash scripts/ci/ci_install_dependency.sh
- name: Run performance test for text models
timeout-minutes: 180
env:
TRACE_BASE_URL: https://raw.githubusercontent.com/sglang-bot/sglang-ci-data/main/traces/${{ github.run_id }}
PERFETTO_RELAY_URL: ${{ vars.PERFETTO_RELAY_URL }}
GPU_CONFIG: "2-gpu-runner"
run: |
cd test/srt
rm -rf performance_profiles_text_models/
python3 nightly/test_text_models_perf.py
- name: Publish traces to storage repo
env:
GITHUB_TOKEN: ${{ secrets.GH_PAT_FOR_NIGHTLY_CI_DATA }}
GITHUB_RUN_ID: ${{ github.run_id }}
GITHUB_RUN_NUMBER: ${{ github.run_number }}
run: |
python3 scripts/ci/publish_traces.py --traces-dir test/srt/performance_profiles_text_models
# VLM accuracy tests
nightly-test-vlm-accuracy-2-gpu-runner:
if: github.repository == 'sgl-project/sglang'
runs-on: 2-gpu-runner
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Install dependencies
run: |
bash scripts/ci/ci_install_dependency.sh
- name: Run eval test for VLM models (fixed MMMU-100)
timeout-minutes: 240
run: |
cd test/srt
python3 nightly/test_vlms_mmmu_eval.py
# VLM performance tests
nightly-test-vlm-perf-2-gpu-runner:
if: github.repository == 'sgl-project/sglang'
runs-on: 2-gpu-runner
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Install dependencies
run: |
bash scripts/ci/ci_install_dependency.sh
- name: Run perf test for VLM models (MMMU)
timeout-minutes: 240
env:
TRACE_BASE_URL: https://raw.githubusercontent.com/sglang-bot/sglang-ci-data/main/traces/${{ github.run_id }}
PERFETTO_RELAY_URL: ${{ vars.PERFETTO_RELAY_URL }}
GPU_CONFIG: "2-gpu-runner"
run: |
cd test/srt
rm -rf performance_profiles_vlms/
python3 nightly/test_vlms_perf.py
- name: Publish traces to storage repo
env:
GITHUB_TOKEN: ${{ secrets.GH_PAT_FOR_NIGHTLY_CI_DATA }}
GITHUB_RUN_ID: ${{ github.run_id }}
GITHUB_RUN_NUMBER: ${{ github.run_number }}
run: |
python3 scripts/ci/publish_traces.py --traces-dir test/srt/performance_profiles_vlms
# B200 Performance tests - 4 GPU
nightly-test-perf-4-gpu-b200:
if: github.repository == 'sgl-project/sglang'
runs-on: 4-gpu-b200
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Install dependencies
run: |
IS_BLACKWELL=1 bash scripts/ci/ci_install_dependency.sh
- name: Run test
timeout-minutes: 60
run: |
cd test/srt
python3 run_suite.py --suite nightly-4-gpu-b200 --continue-on-error
# B200 Performance tests - 8 GPU
nightly-test-perf-8-gpu-b200:
if: github.repository == 'sgl-project/sglang'
runs-on: 8-gpu-b200
env:
RUNNER_LABELS: 8-gpu-b200
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Install dependencies
run: |
IS_BLACKWELL=1 bash scripts/ci/ci_install_dependency.sh
- name: Run DeepSeek v3.1 nightly performance test
timeout-minutes: 180
env:
TRACE_BASE_URL: https://raw.githubusercontent.com/sglang-bot/sglang-ci-data/main/traces/${{ github.run_id }}
PERFETTO_RELAY_URL: ${{ vars.PERFETTO_RELAY_URL }}
GPU_CONFIG: "8-gpu-b200"
run: |
rm -rf test/srt/performance_profiles_deepseek_v31/
cd test/srt
IS_BLACKWELL=1 python3 nightly/test_deepseek_v31_perf.py
- name: Publish DeepSeek v3.1 traces to storage repo
env:
GITHUB_TOKEN: ${{ secrets.GH_PAT_FOR_NIGHTLY_CI_DATA }}
GITHUB_RUN_ID: ${{ github.run_id }}
GITHUB_RUN_NUMBER: ${{ github.run_number }}
run: |
python3 scripts/ci/publish_traces.py --traces-dir test/srt/performance_profiles_deepseek_v31
- name: Run DeepSeek v3.2 nightly performance test
timeout-minutes: 180
env:
TRACE_BASE_URL: https://raw.githubusercontent.com/sglang-bot/sglang-ci-data/main/traces/${{ github.run_id }}
PERFETTO_RELAY_URL: ${{ vars.PERFETTO_RELAY_URL }}
GPU_CONFIG: "8-gpu-b200"
run: |
rm -rf test/srt/performance_profiles_deepseek_v32/
cd test/srt
IS_BLACKWELL=1 python3 nightly/test_deepseek_v32_perf.py
- name: Publish DeepSeek v3.2 traces to storage repo
env:
GITHUB_TOKEN: ${{ secrets.GH_PAT_FOR_NIGHTLY_CI_DATA }}
GITHUB_RUN_ID: ${{ github.run_id }}
GITHUB_RUN_NUMBER: ${{ github.run_number }}
run: |
python3 scripts/ci/publish_traces.py --traces-dir test/srt/performance_profiles_deepseek_v32
# Final check job
check-all-jobs:
if: github.repository == 'sgl-project/sglang' && always()
needs:
- nightly-test-general-1-gpu-runner
- nightly-test-general-4-gpu-h100
- nightly-test-general-8-gpu-h200
- nightly-test-general-8-gpu-h20
- nightly-test-text-accuracy-2-gpu-runner
- nightly-test-text-perf-2-gpu-runner
- nightly-test-vlm-accuracy-2-gpu-runner
- nightly-test-vlm-perf-2-gpu-runner
- nightly-test-perf-4-gpu-b200
- nightly-test-perf-8-gpu-b200
runs-on: ubuntu-latest
steps:
- name: Check if any job failed
run: |
if [[ "${{ contains(needs.*.result, 'failure') }}" == "true" ]]; then
echo "One or more nightly test jobs failed"
exit 1
fi
if [[ "${{ contains(needs.*.result, 'cancelled') }}" == "true" ]]; then
echo "One or more nightly test jobs were cancelled"
exit 1
fi
echo "All nightly test jobs passed"