llama.cpp
metal : add BF16 variant of the tensor API flash attention kernel
#30491

Merged

metal : add BF16 variant of the tensor API flash attention kernel #30491

ggerganov merged 2 commits into ggml-org:master from ethanhq:fa-tensor-bf16

metal : add BF16 variant of the tensor API flash attention kernel

4e34751a

ethanhq requested a review from

ggerganov 28 days ago

ethanhq requested a review 28 days ago

github-actions added testing

github-actions added ggml

github-actions added Apple Metal

ggerganov assigned

ggerganov 28 days ago

ggerganov commented on 2026-10-14

cont : move tensor FA kernels to kernels/fa_tensor.metal

963e7c57

ggerganov approved these changes on 2026-10-15

ggerganov merged 6e66cb5d into master 27 days ago

Reviewers

ggerganov

Assignees

ggerganov

Labels

testing ggml Apple Metal

Milestone

No milestone