llama.cpp
vulkan: Implement split_k for coopmat2 flash attention.
#12627

Merged

vulkan: Implement split_k for coopmat2 flash attention. #12627

jeffbolznv merged 1 commit into ggml-org:master from jeffbolznv:flash_split_k

jeffbolznv requested a review from

0cc4m 1 year ago

github-actions added testing

github-actions added Vulkan

github-actions added ggml

0cc4m approved these changes on 2025-04-02

jeffbolznv force pushed 1 year ago

vulkan: Implement split_k for coopmat2 flash attention.

cc644fb6

jeffbolznv force pushed to cc644fb6 1 year ago

jeffbolznv merged f01bd023 into master 1 year ago

Reviewers

0cc4m

Assignees

No one assigned

Labels

testing Vulkan ggml

Milestone

No milestone