llama.cpp
ggml-cpu/ops: vectorize flash-attention V-cache F16 to F32 conversion
#26947

Merged

ggml-cpu/ops: vectorize flash-attention V-cache F16 to F32 conversion #26947

ggerganov merged 1 commit into ggml-org:master from jinzihao:flash-attn-f16-f32

ggml-cpu/ops: vectorize flash-attention V-cache F16 to F32 conversion

f8503dd9

jinzihao requested a review from

ggerganov 11 days ago

ggml-gh-bot added draft

github-actions added ggml

github-actions marked this pull request as draft 11 days ago

github-actions removed draft

jinzihao marked this pull request as ready for review 11 days ago

am17an approved these changes on 2026-08-12

am17an added merge ready

ggerganov merged eeae28b6 into master 10 days ago

Reviewers

am17an

ggerganov

Assignees

No one assigned

Labels

ggml merge ready

Milestone

No milestone