llama.cpp

308f61c3 - opencl: improve get_rows, cpy, concat and q6_k flat gemv (#24160)

opencl: improve get_rows, cpy, concat and q6_k flat gemv (#24160) * 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