[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
@@ -129,6 +129,7 @@ jobs:
|
||||
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-1gpu }}
|
||||
SGLANG_DIFFUSION_ARTIFACT_DIR: ${{ github.workspace }}/diffusion-failures
|
||||
run: |
|
||||
cd python
|
||||
python3 sglang/multimodal_gen/test/run_suite.py \
|
||||
@@ -146,6 +147,15 @@ jobs:
|
||||
path: python/sglang/multimodal_gen/test/execution_report_*.json
|
||||
retention-days: 1
|
||||
|
||||
- name: Upload diffusion failure artifacts
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: diffusion-failures-1gpu-${{ matrix.part }}-${{ github.run_attempt }}
|
||||
path: diffusion-failures/
|
||||
if-no-files-found: ignore
|
||||
retention-days: 7
|
||||
|
||||
- uses: ./.github/actions/upload-cuda-coredumps
|
||||
if: failure()
|
||||
with:
|
||||
@@ -199,6 +209,7 @@ jobs:
|
||||
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 }}
|
||||
SGLANG_DIFFUSION_ARTIFACT_DIR: ${{ github.workspace }}/diffusion-failures
|
||||
run: |
|
||||
cd python
|
||||
python3 sglang/multimodal_gen/test/run_suite.py \
|
||||
@@ -216,6 +227,15 @@ jobs:
|
||||
path: python/sglang/multimodal_gen/test/execution_report_*.json
|
||||
retention-days: 1
|
||||
|
||||
- name: Upload diffusion failure artifacts
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: diffusion-failures-2gpu-${{ matrix.part }}-${{ github.run_attempt }}
|
||||
path: diffusion-failures/
|
||||
if-no-files-found: ignore
|
||||
retention-days: 7
|
||||
|
||||
- uses: ./.github/actions/upload-cuda-coredumps
|
||||
if: failure()
|
||||
with:
|
||||
@@ -312,19 +332,19 @@ jobs:
|
||||
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-artifacts
|
||||
SGLANG_DIFFUSION_ARTIFACT_DIR: ${{ github.workspace }}/diffusion-failures
|
||||
run: |
|
||||
cd python
|
||||
python3 sglang/multimodal_gen/test/run_suite.py \
|
||||
--suite 1-gpu-b200 \
|
||||
$CONTINUE_ON_ERROR_FLAG
|
||||
|
||||
- name: Upload diffusion artifacts
|
||||
- name: Upload diffusion failure artifacts
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: diffusion-artifacts-${{ github.job }}-${{ github.run_attempt }}
|
||||
path: diffusion-artifacts/
|
||||
name: diffusion-failures-${{ github.job }}-${{ github.run_attempt }}
|
||||
path: diffusion-failures/
|
||||
if-no-files-found: ignore
|
||||
|
||||
- uses: ./.github/actions/upload-cuda-coredumps
|
||||
|
||||
Reference in New Issue
Block a user