]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
opencl: add q5_0 and q5_1 MoE for Adreno (#22985)
authorshaofeiqi <redacted>
Wed, 13 May 2026 18:57:31 +0000 (11:57 -0700)
committerGitHub <redacted>
Wed, 13 May 2026 18:57:31 +0000 (11:57 -0700)
commitec562eb673ab6fef464d0cf976bcb57925b5eff0
tree885d6b3d8f798c9e515ffb6ad3216c31b505d53d
parent95d469a915333eb2e14eff9b02b49292716389cd
opencl: add q5_0 and q5_1 MoE for Adreno (#22985)

* opencl: add q5_0 moe support

* opencl: add q5_1 moe support

* opencl: avoid potential leak

* opencl: suppress unused var warning when building for non-Adreno

---------

Co-authored-by: Li He <redacted>
ggml/src/ggml-opencl/CMakeLists.txt
ggml/src/ggml-opencl/ggml-opencl.cpp
ggml/src/ggml-opencl/kernels/cvt.cl
ggml/src/ggml-opencl/kernels/gemm_moe_q5_0_f32_ns.cl [new file with mode: 0644]
ggml/src/ggml-opencl/kernels/gemm_moe_q5_1_f32_ns.cl [new file with mode: 0644]
ggml/src/ggml-opencl/kernels/gemv_moe_q5_0_f32_ns.cl [new file with mode: 0644]
ggml/src/ggml-opencl/kernels/gemv_moe_q5_1_f32_ns.cl [new file with mode: 0644]