ci: migrate 2-GPU tests to test/registered/ (#16529)

This commit is contained in:
Alison Shao
2026-01-07 20:28:16 -08:00
committed by GitHub
parent ab7d5829cd
commit 63cc97f4ef
15 changed files with 84 additions and 80 deletions

View File

@@ -674,6 +674,10 @@ jobs:
runs-on: 2-gpu-runner
env:
RUNNER_LABELS: 2-gpu-runner
strategy:
fail-fast: false
matrix:
partition: [0, 1]
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -700,7 +704,7 @@ jobs:
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
CONTINUE_ON_ERROR_FLAG="--continue-on-error"
fi
python3 run_suite.py --hw cuda --suite stage-b-test-large-2-gpu $CONTINUE_ON_ERROR_FLAG
python3 run_suite.py --hw cuda --suite stage-b-test-large-2-gpu --auto-partition-id ${{ matrix.partition }} --auto-partition-size 2 $CONTINUE_ON_ERROR_FLAG
stage-c-test-large-4-gpu:
needs: [check-changes, call-gate, stage-b-test-small-1-gpu, stage-b-test-large-1-gpu, stage-b-test-large-2-gpu, sgl-kernel-build-wheels]
@@ -1027,57 +1031,6 @@ jobs:
IS_BLACKWELL=1 python3 run_suite.py --hw cuda --suite stage-b-test-4-gpu-b200 $CONTINUE_ON_ERROR_FLAG
unit-test-backend-2-gpu:
needs: [check-changes, call-gate, unit-test-backend-1-gpu]
if: |
always() &&
(
(inputs.target_stage == 'unit-test-backend-2-gpu') ||
(
!inputs.target_stage &&
(github.event_name == 'schedule' || (!failure() && !cancelled())) &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
)
)
runs-on: 2-gpu-runner
env:
RUNNER_LABELS: 2-gpu-runner
strategy:
fail-fast: false
matrix:
part: [0, 1]
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
- name: Download artifacts
if: needs.check-changes.outputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda12.9
- name: Install dependencies
run: |
CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} bash scripts/ci/ci_install_dependency.sh
- name: Run test
timeout-minutes: 30
run: |
cd test/srt
RETRY_FLAG=""
if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
RETRY_FLAG="--enable-retry"
fi
CONTINUE_ON_ERROR_FLAG=""
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
CONTINUE_ON_ERROR_FLAG="--continue-on-error"
fi
python3 run_suite.py --suite per-commit-2-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
unit-test-backend-4-gpu:
needs: [check-changes, call-gate, unit-test-backend-1-gpu, stage-b-test-4-gpu-b200]
if: |
@@ -1802,7 +1755,6 @@ jobs:
stage-c-test-large-4-gpu,
quantization-test,
unit-test-backend-1-gpu,
unit-test-backend-2-gpu,
stage-b-test-4-gpu-b200,
unit-test-backend-4-gpu,
unit-test-backend-8-gpu-h20,