llama.cpp
webgpu: support per-head flash attention masks
#32394
Merged

webgpu: support per-head flash attention masks #32394

ServeurpersoCom
ServeurpersoCom webgpu: support per-head flash attention masks
713499e6
ServeurpersoCom ServeurpersoCom requested a review 1 day ago
ngxson
ngxson approved these changes on 2026-11-16
github-actions github-actions added ggml
github-actions github-actions added WebGPU
yomaytk
yomaytk approved these changes on 2026-11-16
ServeurpersoCom ServeurpersoCom merged 164ab018 into master 1 day ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone