llama.cpp
ggml-webgpu: makes the flash attn vec path subgroup-aware
#23040
Merged

ggml-webgpu: makes the flash attn vec path subgroup-aware #23040

ArberSephirotheca
ArberSephirotheca ggml-webgpu: makes the flash attn vec path compile and size its split…
4c0f6291
ArberSephirotheca ArberSephirotheca requested a review 49 days ago
github-actions github-actions added ggml
github-actions github-actions added WebGPU
reeselevine
reeselevine commented on 2026-05-14
ArberSephirotheca ggml-webgpu: remove the extra max_wg_size >= max_subgroup_size guard.…
d53c0c1b
reeselevine
reeselevine approved these changes on 2026-05-14
reeselevine reeselevine requested a review from CISC CISC 49 days ago
CISC
CISC approved these changes on 2026-05-14
reeselevine reeselevine merged 5ec717d1 into master 49 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone