llama.cpp
OpenCL: add attention sinks support for FA kernels
#15706

Merged

OpenCL: add attention sinks support for FA kernels #15706

lhez merged 1 commit into ggml-org:master from rmatif:add-attn-sinks-fa

add attn sinks support for FA kernels

b27e95a7

rmatif requested a review from

max-krasnyansky 68 days ago

rmatif requested a review from

lhez 68 days ago

github-actions added ggml

github-actions added OpenCL

lhez approved these changes on 2025-09-02

lhez merged 97669e40 into master 66 days ago

Reviewers

lhez

max-krasnyansky

Assignees

No one assigned

Labels

ggml OpenCL

Milestone

No milestone