Skip to content

CUDA: Optimize GDN PP perf#20449

Closed
ORippler wants to merge 12 commits into
ggml-org:gg/gdn-fix-state-transposefrom
ORippler:osimons/gdn-pp-optimizations
Closed

CUDA: Optimize GDN PP perf#20449
ORippler wants to merge 12 commits into
ggml-org:gg/gdn-fix-state-transposefrom
ORippler:osimons/gdn-pp-optimizations

Pull attn_writes out of the compute loop for no_tail

33ee71b
Select commit
Loading
Failed to load commit list.
Sign in for the full log view

Annotations

1 error

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