]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 335abed)
opencl: add basic support for q5_0 and q5_1 (#23548)
authorshaofeiqi <redacted>
Mon, 1 Jun 2026 17:06:50 +0000 (10:06 -0700)
committerGitHub <redacted>
Mon, 1 Jun 2026 17:06:50 +0000 (10:06 -0700)
commit27d9ed839713e31c7a0ba45e342109a04549834f
tree93161facb99fdb99e10cb2ae97adc06afb92f13atree
parent335abed17decc19ba9e975c0e913ace56d4d722bcommit | diff
opencl: add basic support for q5_0 and q5_1 (#23548)

* opencl: add general q5_0 support

* opencl: add general q5_1 support

* opencl: support non-uniform workgrp size

---------

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/mul_mm_q5_0_f32_l4_lm.cl [new file with mode: 0644] blob
ggml/src/ggml-opencl/kernels/mul_mm_q5_1_f32_l4_lm.cl [new file with mode: 0644] blob
ggml/src/ggml-opencl/kernels/mul_mv_q5_0_f32.cl [new file with mode: 0644] blob
ggml/src/ggml-opencl/kernels/mul_mv_q5_0_f32_flat.cl [new file with mode: 0644] blob
ggml/src/ggml-opencl/kernels/mul_mv_q5_1_f32.cl [new file with mode: 0644] blob
ggml/src/ggml-opencl/kernels/mul_mv_q5_1_f32_flat.cl [new file with mode: 0644] blob
Packaging of ggml-org/llama.cpp