Disable unit-test-deepep-8-gpu (#17176)

This commit is contained in:
Alison Shao
2026-01-15 15:12:45 -08:00
committed by GitHub
parent 8b99af9af8
commit 69822c7271
2 changed files with 55 additions and 51 deletions

View File

@@ -1614,53 +1614,54 @@ jobs:
fi
python3 run_suite.py --suite per-commit-4-gpu-deepep $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
unit-test-deepep-8-gpu:
needs: [check-changes, call-gate, stage-b-test-small-1-gpu, stage-b-test-large-1-gpu, stage-b-test-large-2-gpu, stage-b-test-4-gpu-b200]
if: |
always() &&
(
(inputs.target_stage == 'unit-test-deepep-8-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: 8-gpu-h200
env:
RUNNER_LABELS: 8-gpu-h200
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
- name: Download artifacts
if: needs.check-changes.outputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda12.9
- name: Install dependencies
timeout-minutes: 10
run: |
CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} bash scripts/ci/ci_install_deepep.sh
- name: Run test
timeout-minutes: 20
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-8-gpu-h200-deepep $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
# Disabled: IBGDA/cudaHostRegister environment issues on 8-GPU runner, see #17175
# unit-test-deepep-8-gpu:
# needs: [check-changes, call-gate, stage-b-test-small-1-gpu, stage-b-test-large-1-gpu, stage-b-test-large-2-gpu, stage-b-test-4-gpu-b200]
# if: |
# always() &&
# (
# (inputs.target_stage == 'unit-test-deepep-8-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: 8-gpu-h200
# env:
# RUNNER_LABELS: 8-gpu-h200
# steps:
# - name: Checkout code
# uses: actions/checkout@v4
# with:
# ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
#
# - name: Download artifacts
# if: needs.check-changes.outputs.sgl_kernel == 'true'
# uses: actions/download-artifact@v4
# with:
# path: sgl-kernel/dist/
# merge-multiple: true
# pattern: wheel-python3.10-cuda12.9
#
# - name: Install dependencies
# timeout-minutes: 10
# run: |
# CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} bash scripts/ci/ci_install_deepep.sh
#
# - name: Run test
# timeout-minutes: 20
# 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-8-gpu-h200-deepep $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
unit-test-backend-4-gpu-b200:
needs: [check-changes, call-gate, stage-b-test-small-1-gpu, stage-b-test-large-1-gpu, stage-b-test-large-2-gpu, stage-b-test-4-gpu-b200]
@@ -1800,7 +1801,7 @@ jobs:
accuracy-test-1-gpu,
accuracy-test-2-gpu,
unit-test-deepep-4-gpu,
unit-test-deepep-8-gpu,
# unit-test-deepep-8-gpu, # Disabled, see #17175
unit-test-backend-4-gpu-b200,
unit-test-backend-4-gpu-gb200,
]