[diffusion] CI: add minimax-h3 2-gpu consistency coverage (#33281)

This commit is contained in:
Mick
2026-08-03 22:40:08 +08:00
committed by GitHub
parent 3953788596
commit 0ba46c88e5
7 changed files with 164 additions and 53 deletions
+4 -1
View File
@@ -364,7 +364,8 @@ jobs:
--target-time 1800 \
--max-time 2400 \
--max-partitions 10 \
--parametrized-only
--parametrized-only \
${{ inputs.case_ids != '' && format('--case-ids {0}', inputs.case_ids) || '' }}
multimodal-diffusion-gen-1gpu:
needs: compute-diffusion-partitions
@@ -480,6 +481,8 @@ jobs:
- name: Generate outputs
env:
HF_TOKEN: ${{ secrets.MINIMAX_H3_HF_TOKEN || secrets.SGLANG_DIFFUSION_CI_HF_TOKEN || secrets.HF_TOKEN }}
HUGGING_FACE_HUB_TOKEN: ${{ secrets.MINIMAX_H3_HF_TOKEN || secrets.SGLANG_DIFFUSION_CI_HF_TOKEN || secrets.HF_TOKEN }}
RUNAI_STREAMER_MEMORY_LIMIT: 0
PARTITION_PLAN_JSON: ${{ needs.compute-diffusion-partitions.outputs.plan-2gpu }}
run: |
+2 -49
View File
@@ -301,6 +301,8 @@ jobs:
- name: Run diffusion server tests
timeout-minutes: 240
env:
HF_TOKEN: ${{ secrets.MINIMAX_H3_HF_TOKEN || secrets.SGLANG_DIFFUSION_CI_HF_TOKEN || secrets.HF_TOKEN }}
HUGGING_FACE_HUB_TOKEN: ${{ secrets.MINIMAX_H3_HF_TOKEN || secrets.SGLANG_DIFFUSION_CI_HF_TOKEN || secrets.HF_TOKEN }}
RUNAI_STREAMER_MEMORY_LIMIT: 0
CONTINUE_ON_ERROR_FLAG: ${{ inputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
PARTITION_PLAN_JSON: ${{ needs.compute-diffusion-partitions.outputs.plan-2gpu }}
@@ -435,55 +437,6 @@ jobs:
- uses: ./.github/actions/upload-cuda-coredumps
if: failure()
multimodal-gen-test-4-h100:
# Temporarily disabled while the 4-gpu-h100 runner is unstable
if: ${{ false }}
runs-on: 4-gpu-h100
timeout-minutes: 90
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.git_ref || github.sha }}
- uses: ./.github/actions/check-pr-test-health
- uses: ./.github/actions/check-maintenance
- name: Download artifacts
if: inputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda*
- name: Install dependencies
timeout-minutes: 20
run: |
CUSTOM_BUILD_SGL_KERNEL=${{inputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh diffusion
- name: Run MiniMax-H3 PR smoke test
timeout-minutes: 45
env:
RUNAI_STREAMER_MEMORY_LIMIT: 0
SGLANG_TEST_WAIT_SECS: 1800
SGLANG_DIFFUSION_ARTIFACT_DIR: ${{ github.workspace }}/diffusion-failures
run: |
cd python
python3 sglang/multimodal_gen/test/run_suite.py --suite 4-gpu-h100
- name: Upload diffusion failure artifacts
if: always()
uses: actions/upload-artifact@v4
with:
name: diffusion-failures-${{ github.job }}-${{ github.run_attempt }}
path: diffusion-failures/
if-no-files-found: ignore
- uses: ./.github/actions/upload-cuda-coredumps
if: failure()
multimodal-gen-unit-test:
if: |
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == 'true') || (inputs.caller_needs_failure != 'true' && !cancelled())) &&