Skip to content
Back to pull request #1281

[triton] Support head_dim not 2^n in triton extend and decode attention #134

Sign in to view logs

[triton] Support head_dim not 2^n in triton extend and decode attention

[triton] Support head_dim not 2^n in triton extend and decode attention #134

Annotations

1 warning

The logs for this run have expired and are no longer available.