[diffusion] CI: add 5090 job (#29791)

This commit is contained in:
Mick
2026-07-01 19:09:43 +08:00
committed by GitHub
parent 7d9de81cda
commit 79f334b1aa
16 changed files with 731 additions and 85 deletions
@@ -144,6 +144,69 @@ jobs:
with:
artifact-suffix: ${{ matrix.part }}
multimodal-gen-test-1-5090:
if: |
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == 'true') || (inputs.caller_needs_failure != 'true' && !cancelled())) &&
inputs.multimodal_gen == 'true'
runs-on: 1-gpu-5090
timeout-minutes: 180
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.git_ref || github.sha }}
- uses: ./.github/actions/check-pr-test-health
- uses: ./.github/actions/check-maintenance
- name: Download artifacts
if: inputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda*
- name: Install dependencies
timeout-minutes: 20
run: |
CUSTOM_BUILD_SGL_KERNEL=${{inputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh diffusion
- name: Run 5090 diffusion canary tests
timeout-minutes: 120
env:
RUNAI_STREAMER_MEMORY_LIMIT: 0
CONTINUE_ON_ERROR_FLAG: ${{ inputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
SGLANG_DIFFUSION_ARTIFACT_DIR: ${{ github.workspace }}/diffusion-failures
run: |
cd python
python3 sglang/multimodal_gen/test/run_suite.py \
--suite 1-gpu-5090 \
$CONTINUE_ON_ERROR_FLAG
- name: Upload execution report
if: always()
uses: actions/upload-artifact@v4
with:
name: diffusion-5090-report-${{ github.run_attempt }}
path: python/sglang/multimodal_gen/test/execution_report_*.json
retention-days: 7
- name: Upload diffusion failure artifacts
if: always()
uses: actions/upload-artifact@v4
with:
name: diffusion-failures-5090-${{ github.run_attempt }}
path: diffusion-failures/
if-no-files-found: ignore
retention-days: 7
- uses: ./.github/actions/upload-cuda-coredumps
if: failure()
with:
artifact-suffix: 1-gpu-5090
multimodal-gen-test-2-gpu:
needs: compute-diffusion-partitions
if: |