llama.cpp
webgpu: support per-head flash attention masks
#32394
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
1
Changes
View On
GitHub
webgpu: support per-head flash attention masks
#32394
ServeurpersoCom
merged 1 commit into
master
from
pascal/webgpu-fa-mask-heads
webgpu: support per-head flash attention masks
713499e6
ServeurpersoCom
requested a review
1 day ago
ngxson
approved these changes on 2026-11-16
github-actions
added
ggml
github-actions
added
WebGPU
yomaytk
approved these changes on 2026-11-16
ServeurpersoCom
merged
164ab018
into master
1 day ago
Login to write a write a comment.
Login via GitHub
Reviewers
yomaytk
ngxson
Assignees
No one assigned
Labels
ggml
WebGPU
Milestone
No milestone
Login to write a write a comment.
Login via GitHub