]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 49a7564)
opencl: add optimized q4_1 mm kernel for adreno (#19840)
authorshaofeiqi <redacted>
Tue, 3 Mar 2026 03:49:41 +0000 (19:49 -0800)
committerGitHub <redacted>
Tue, 3 Mar 2026 03:49:41 +0000 (19:49 -0800)
commit24350fdf9bc53aaf28d695f60a7bf5641d370698
treeb78d37a5e7cbd025eb5ae2b71c30dc1b576fad7btree
parent49a7564ac1e845d7d7d61e9236242282dc5d8248commit | diff
opencl: add optimized q4_1 mm kernel for adreno (#19840)

* Add Q4_1 OpenCL Kernels

* opencl: refactor transpose

* opencl: format

* opencl: refactor q4_1 unpack

* opencl: move `ggml_cl_mul_mat_q4_1_f32_adreno`

* opencl: refactor `ggml_cl_mul_mat_q4_1_f32_adreno` and kernels

* opencl: rename kernel files and kernes

* opencl: fix build for non adreno

* opencl: move code around and format

---------

Co-authored-by: Li He <redacted>
ggml/src/ggml-opencl/CMakeLists.txt diff | blob | history
ggml/src/ggml-opencl/ggml-opencl.cpp diff | blob | history
ggml/src/ggml-opencl/kernels/cvt.cl diff | blob | history
ggml/src/ggml-opencl/kernels/gemm_noshuffle_q4_1_f32.cl [new file with mode: 0644] blob
ggml/src/ggml-opencl/kernels/gemv_noshuffle_general_q8_0_f32.cl diff | blob | history
ggml/src/ggml-opencl/kernels/gemv_noshuffle_q4_1_f32.cl [new file with mode: 0644] blob
ggml/src/ggml-opencl/kernels/transpose.cl diff | blob | history
Packaging of ggml-org/llama.cpp