[Dependency] Upgrade to Torch 2.11.0 (#21247)
Co-authored-by: Kangyan Zhou <zky314343421@gmail.com> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com> Co-authored-by: b8zhong <b8zhong@users.noreply.github.com> Co-authored-by: Mick <mickjagger19@icloud.com>
This commit is contained in:
co-authored by
Kangyan Zhou
Claude Opus 4.7
Baizhou Zhang
b8zhong
Mick
parent
24a6b3084d
commit
88bb5dffe4
@@ -68,6 +68,8 @@ env:
|
||||
SGLANG_CUDA_COREDUMP: "1"
|
||||
SGLANG_JIT_DEEPGEMM_FAST_WARMUP: true
|
||||
SKIP_STAGE_HEALTH_CHECK: ${{ inputs.skip_stage_health_check == true && 'true' || 'false' }}
|
||||
# TEMP: rebuild deepep against the new torch for torch-211-merge PR only — revert before merging to main.
|
||||
FORCE_REBUILD_DEEPEP: '1'
|
||||
# Schedule / main-branch dispatch / workflow_call from main use refs/heads/main; PR events use refs/pull/*/merge
|
||||
PR_TEST_BYPASS_MAINTENANCE_ON_MAIN: ${{ github.ref == 'refs/heads/main' && 'true' || 'false' }}
|
||||
USE_VENV: false
|
||||
@@ -610,11 +612,18 @@ jobs:
|
||||
# =============================================== jit-kernel ====================================================
|
||||
|
||||
call-jit-kernel-tests:
|
||||
needs: [check-changes, call-gate]
|
||||
if: needs.check-changes.outputs.jit_kernel == 'true'
|
||||
needs: [check-changes, call-gate, sgl-kernel-build-wheels]
|
||||
if: |
|
||||
always() &&
|
||||
!failure() && !cancelled() &&
|
||||
github.event_name != 'schedule' &&
|
||||
inputs.test_parallel_dispatch != true &&
|
||||
!inputs.target_stage &&
|
||||
needs.check-changes.outputs.jit_kernel == 'true'
|
||||
uses: ./.github/workflows/pr-test-jit-kernel.yml
|
||||
with:
|
||||
jit_kernel: ${{ needs.check-changes.outputs.jit_kernel }}
|
||||
sgl_kernel: ${{ needs.check-changes.outputs.sgl_kernel }}
|
||||
b200_runner: ${{ needs.check-changes.outputs.b200_runner }}
|
||||
pr_head_sha: ${{ inputs.pr_head_sha || '' }}
|
||||
git_ref: ${{ inputs.git_ref || '' }}
|
||||
@@ -971,7 +980,7 @@ jobs:
|
||||
CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh
|
||||
|
||||
- name: Run test
|
||||
timeout-minutes: 30
|
||||
timeout-minutes: 40
|
||||
env:
|
||||
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
|
||||
run: |
|
||||
@@ -1175,10 +1184,6 @@ jobs:
|
||||
env:
|
||||
SGLANG_CI_RDMA_ALL_DEVICES: "mlx5_1,mlx5_2,mlx5_3,mlx5_4"
|
||||
CU_VERSION: cu129
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
part: [0, 1]
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
@@ -1208,12 +1213,10 @@ jobs:
|
||||
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
|
||||
run: |
|
||||
cd test
|
||||
python3 run_suite.py --hw cuda --suite stage-c-test-8-gpu-h20 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 $CONTINUE_ON_ERROR_FLAG
|
||||
python3 run_suite.py --hw cuda --suite stage-c-test-8-gpu-h20 $CONTINUE_ON_ERROR_FLAG
|
||||
|
||||
- uses: ./.github/actions/upload-cuda-coredumps
|
||||
if: failure()
|
||||
with:
|
||||
artifact-suffix: ${{ matrix.part }}
|
||||
|
||||
- name: Cleanup venv
|
||||
if: always()
|
||||
|
||||
Reference in New Issue
Block a user