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

webgpu: support per-head flash attention masks #32394

ServeurpersoCom wants to merge 1 commit into master from pascal/webgpu-fa-mask-heads
ServeurpersoCom
ServeurpersoCom webgpu: support per-head flash attention masks
713499e6
ServeurpersoCom ServeurpersoCom requested a review 1 hour ago
ngxson
ngxson approved these changes on 2026-11-16
github-actions github-actions added ggml
github-actions github-actions added WebGPU

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone