llama.cpp
ggml-webgpu: Fix bug in FlashAttention support check
#22492

Merged

ggml-webgpu: Fix bug in FlashAttention support check #22492

ggerganov merged 2 commits into ggml-org:master from reeselevine:flashattn-support-fix

Fix flashattention support check for devices that don't support subgr…

70a4f4f6

reeselevine requested a review 58 days ago

github-actions added ggml

github-actions added WebGPU

ArberSephirotheca commented on 2026-04-29

set path to none if kv_tile doesn't fit

49db7ee5

ArberSephirotheca approved these changes on 2026-04-29

reeselevine added merge ready

CISC approved these changes on 2026-04-29

ggerganov merged d6a50940 into master 58 days ago

Reviewers

CISC

ArberSephirotheca

Assignees

No one assigned

Labels

ggml merge ready WebGPU

Milestone

No milestone