llama.cpp
opencl: route large narrow-hidden q6_K lm_head to the flat GEMV
#26427

Merged

opencl: route large narrow-hidden q6_K lm_head to the flat GEMV #26427

max-krasnyansky merged 1 commit into ggml-org:master from qualcomm:hq/q6k-flat-large-m-size-gate-r0730

wanghqc requested a review 91 days ago

github-actions added ggml

github-actions added OpenCL

opencl: route large q6_K lm_head to the flat GEMV

21838625

lhez force pushed to 21838625 90 days ago

lhez approved these changes on 2026-08-03

max-krasnyansky approved these changes on 2026-08-03

max-krasnyansky merged 39eab74a into master 89 days ago

Reviewers

max-krasnyansky

lhez

Assignees

No one assigned

Labels

ggml OpenCL

Milestone

No milestone