Skip to content

Bumping flash attention version to 2.6.3 and adding option for softcap in attention and lm_head logits. #3652

Bumping flash attention version to 2.6.3 and adding option for softcap in attention and lm_head logits.

Bumping flash attention version to 2.6.3 and adding option for softcap in attention and lm_head logits. #3652

Triggered via pull request July 19, 2024 23:47
Status Cancelled
Total duration 1m 29s
Artifacts

smoketest.yaml

on: pull_request
Matrix: smoketest
Fit to window
Zoom out
Zoom in

Annotations

2 errors
smoketest (3.10)
Canceling since a higher priority waiting request for 'Smoketest-1374' exists
smoketest (3.9)
Canceling since a higher priority waiting request for 'Smoketest-1374' exists