Skip to content

Commit b2d689a

Browse files
jeffbolznvjeffbolznv
committed
vulkan: Update topk_moe fusion to handle gpt's late softmax
Based on ggml-org#16649.
1 parent 4926419 commit b2d689a

File tree

2 files changed

+251
-113
lines changed

2 files changed

+251
-113
lines changed

0 commit comments

Comments
 (0)