minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[CI]Add gb200 runner back (#15024)

Browse Source
This commit is contained in:
Baizhou Zhang
2025-12-12 20:19:34 -08:00
committed by GitHub
parent 291396544e
commit 8698867479
2 changed files with 37 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/pr-test.yml
+36 -38
View File
@@ -1228,45 +1228,44 @@ jobs:
cd test/srt cd test/srt
IS_BLACKWELL=1 python3 run_suite.py --suite per-commit-4-gpu-b200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 1800 IS_BLACKWELL=1 python3 run_suite.py --suite per-commit-4-gpu-b200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 1800
# TODO: Add gb200 tests back after the ci runner is fixed unit-test-backend-4-gpu-gb200:
# unit-test-backend-4-gpu-gb200: needs: [check-changes, call-gate, unit-test-backend-2-gpu, sgl-kernel-build-wheels-arm]
# needs: [check-changes, call-gate, unit-test-backend-2-gpu, sgl-kernel-build-wheels-arm] if: |
# if: | always() &&
# always() && (
# ( (inputs.target_stage == 'unit-test-backend-4-gpu-gb200') ||
# (inputs.target_stage == 'unit-test-backend-4-gpu-gb200') || (
# ( !inputs.target_stage &&
# !inputs.target_stage && (github.event_name == 'schedule' || (!failure() && !cancelled())) &&
# (github.event_name == 'schedule' || (!failure() && !cancelled())) && ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
# ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true')) )
# ) )
# ) runs-on: 4-gpu-gb200
# runs-on: 4-gpu-gb200 env:
# env: RUNNER_LABELS: 4-gpu-gb200
# RUNNER_LABELS: 4-gpu-gb200 strategy:
# strategy: fail-fast: false
# fail-fast: false steps:
# steps: - name: Checkout code
# - name: Checkout code uses: actions/checkout@v4
# uses: actions/checkout@v4
# - name: Download artifacts - name: Download artifacts
# if: needs.check-changes.outputs.sgl_kernel == 'true' if: needs.check-changes.outputs.sgl_kernel == 'true'
# uses: actions/download-artifact@v4 uses: actions/download-artifact@v4
# with: with:
# path: sgl-kernel/dist/ path: sgl-kernel/dist/
# merge-multiple: true merge-multiple: true
# pattern: wheel-python3.10-cuda12.9-aarch64 pattern: wheel-python3.10-cuda12.9-aarch64
# - name: Install dependencies - name: Install dependencies
# run: | run: |
# CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} IS_BLACKWELL=1 GRACE_BLACKWELL=1 bash scripts/ci/ci_install_deepep.sh CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} IS_BLACKWELL=1 GRACE_BLACKWELL=1 bash scripts/ci/ci_install_deepep.sh
# - name: Run test - name: Run test
# timeout-minutes: 45 timeout-minutes: 45
# run: | run: |
# cd test/srt cd test/srt
# python3 run_suite.py --suite per-commit-4-gpu-gb200 --auto-partition-id 0 --auto-partition-size 1 --timeout-per-file 3600 python3 run_suite.py --suite per-commit-4-gpu-gb200 --auto-partition-id 0 --auto-partition-size 1 --timeout-per-file 3600
pr-test-finish: pr-test-finish:
needs: needs:
@@ -1300,8 +1299,7 @@ jobs:
unit-test-deepep-4-gpu, unit-test-deepep-4-gpu,
unit-test-deepep-8-gpu, unit-test-deepep-8-gpu,
unit-test-backend-4-gpu-b200, unit-test-backend-4-gpu-b200,
# unit-test-backend-4-gpu-gb200, unit-test-backend-4-gpu-gb200,
# unit-test-backend-8-gpu-b200, # Moved to nightly - large models only
] ]
if: always() if: always()
runs-on: ubuntu-latest runs-on: ubuntu-latest
test/srt/test_deepseek_v3_cutedsl_4gpu.py
+1 -1
View File
@@ -23,7 +23,7 @@ class TestDeepseekR1Nvfp4CuteDSLDeepEP(CustomTestCase):
"--trust-remote-code", "--trust-remote-code",
"--disable-radix-cache", "--disable-radix-cache",
"--mem-fraction-static", "--mem-fraction-static",
"0.89", "0.8",
"--max-prefill-tokens", "--max-prefill-tokens",
"16384", "16384",
"--max-running-requests", "--max-running-requests",