]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
opencl: improve get_rows, cpy, concat and q6_k flat gemv (llama/24160)
authorlhez <redacted>
Fri, 5 Jun 2026 20:45:25 +0000 (13:45 -0700)
committerGeorgi Gerganov <redacted>
Mon, 8 Jun 2026 11:36:36 +0000 (14:36 +0300)
commita87e950a0634481140473324e346badd458ff11f
tree597597658fb95f836d8841a78d0ba182ecf7f831
parent5a1feed8ca57b70d002ca0df2abd3db9328a1daa
opencl: improve get_rows, cpy, concat and q6_k flat gemv (llama/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
ggml/src/ggml-opencl/ggml-opencl.cpp
ggml/src/ggml-opencl/kernels/concat.cl
ggml/src/ggml-opencl/kernels/cpy.cl
ggml/src/ggml-opencl/kernels/get_rows.cl
ggml/src/ggml-opencl/kernels/mul_mv_q6_k_f32_flat.cl