[decoding_attention] Fix broken flash_attention and xformers #302
Triggered via pull request
December 9, 2024 13:12
xuzhao9
Status
Failure
Total duration
4h 0m 35s
Artifacts
–
pr.yaml
on: pull_request
h100-pytorch-test
/
linux-test-h100
4h 0m
h100-triton-main-test
/
linux-test-h100
4h 0m
Annotations
4 errors
|
h100-pytorch-test / linux-test-h100
The job running on runner gcp-h100-runner-hl226-runner-qfcgj has exceeded the maximum execution time of 240 minutes.
|
|
h100-pytorch-test / linux-test-h100
The operation was canceled.
|
|
h100-triton-main-test / linux-test-h100
The job running on runner gcp-h100-runner-hl226-runner-7rwdn has exceeded the maximum execution time of 240 minutes.
|
|
h100-triton-main-test / linux-test-h100
The operation was canceled.
|