llama.cpp
opencl: add bin kernel `kernel_gemm_noshuffle_q4_k_f32_32b_trans_ila_a8_bin`
#28677

Merged

opencl: add bin kernel `kernel_gemm_noshuffle_q4_k_f32_32b_trans_ila_a8_bin` #28677

lhez merged 3 commits into ggml-org:master from qualcomm:q4_k-a8-bin-kernel

github-actions added ggml

github-actions added OpenCL

lhez force pushed from 0dd3c835 to 0103505f 16 days ago

lhez force pushed from 0103505f to cda14956 16 days ago

lhez marked this pull request as ready for review 16 days ago

lhez requested a review 16 days ago

lhez approved these changes on 2026-09-11

lhez requested a review from

max-krasnyansky 16 days ago

max-krasnyansky approved these changes on 2026-09-11

max-krasnyansky commented on 2026-09-11

opencl: add A8 Q4_K non-MoE binary kernel

13d64f69

opencl: fix layout compatibility

758b9448

opencl: rename binary kernel selection helpers

a719272b

shaofeiqi force pushed from cda14956 to a719272b 16 days ago

lhez approved these changes on 2026-09-11

lhez merged 07fc9771 into master 15 days ago

Reviewers

lhez

max-krasnyansky

Assignees

No one assigned

Labels

ggml OpenCL

Milestone

No milestone