[ci]use H20 to run disaggregation test (#11543)

This commit is contained in:
Hank Han
2025-10-17 02:42:42 +08:00
committed by GitHub
parent 0975ba99bc
commit 0dd6cf16ba
6 changed files with 75 additions and 128 deletions

View File

@@ -350,6 +350,39 @@ jobs:
cd test/srt
python3 run_suite.py --suite per-commit-8-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
unit-test-backend-8-gpu-h20:
needs: [check-changes, unit-test-backend-2-gpu, sgl-kernel-build-wheels]
if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 8-gpu-h20
env:
SGLANG_CI_RDMA_ALL_DEVICES: "mlx5_1,mlx5_2,mlx5_3,mlx5_4"
strategy:
fail-fast: false
matrix:
part: [0, 1]
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Download artifacts
if: needs.check-changes.outputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda12.9
- name: Install dependencies
run: |
CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} bash scripts/ci/ci_install_dependency.sh
- name: Run test
timeout-minutes: 20
run: |
cd test/srt
python3 run_suite.py --suite per-commit-8-gpu-h20 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
performance-test-1-gpu-part-1:
needs: [check-changes, sgl-kernel-build-wheels]
if: always() && !failure() && !cancelled() &&