]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 8e1f9d0)
opencl: add q4_1 MoE for Adreno (#22856)
authorShawn Gu <redacted>
Mon, 11 May 2026 18:57:26 +0000 (11:57 -0700)
committerGitHub <redacted>
Mon, 11 May 2026 18:57:26 +0000 (11:57 -0700)
commit1ec7ba0c14f33f17e980daeeda5f35b225d41994
tree94ed081b114d58bcf44f94f323ce6eb3f1fe372atree
parent8e1f9d083453678808a26465a3563a19a0b49699commit | diff
opencl: add q4_1 MoE for Adreno (#22856)

* Q4_1 MoE CLC pass sanity check

* remove unnecessary code

* opencl: remove unnecessary asserts and reformat

* opencl: fix supports_op for q4_1 moe

* q4_1 moe is supported by Adreno with certain shapes

---------

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_moe_q4_1_f32_ns.cl [new file with mode: 0644] blob
ggml/src/ggml-opencl/kernels/gemv_moe_q4_1_f32_ns.cl [new file with mode: 0644] blob
Packaging of ggml-org/llama.cpp