Skip to content

[Relax][cuDNN] Do not offload causal / non-fp16 attention, and fix the default softmax scale - #20078

Open
YangXu1990uiuc wants to merge 1 commit into
apache:mainfrom
YangXu1990uiuc:yanxu/cudnn-sdpa-fixes
Open

[Relax][cuDNN] Do not offload causal / non-fp16 attention, and fix the default softmax scale#20078
YangXu1990uiuc wants to merge 1 commit into
apache:mainfrom
YangXu1990uiuc:yanxu/cudnn-sdpa-fixes

[Relax][cuDNN] Reject unsupported attention offloads; fix default scale

d76e4c6
Select commit
Loading
Failed to load commit list.

Workflow runs completed with no jobs