mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-06-28 07:10:21 +00:00
308f61c31f
* opencl: allow multiple workgroups for large rows * opencl: improve small cpy * opencl: packed concat for small input * opencl: tweak flat q6_K gemv, increase N_DST and remap threads