Skip to content
PR CPU tests

Fix flash attention GQA bug to use the dynamic size of the key/value tensors - used for eval/inference #3110

Sign in to view logs

Fix flash attention GQA bug to use the dynamic size of the key/value tensors - used for eval/inference

Fix flash attention GQA bug to use the dynamic size of the key/value tensors - used for eval/inference #3110

Run time

Learn about OS pricing on GitHub Actions
Job Run time
cpu-1.13.1 / pytest-cpu
10m 0s
cpu-2.1.0 / pytest-cpu
9m 50s
Coverage Results / coverage
11s
20m 1s