]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: cce09f0)
opencl: add opt-in Adreno xmem F16xF32 GEMM for prefill (#22755)
authoryzyyzyhhh <redacted>
Tue, 12 May 2026 20:10:37 +0000 (04:10 +0800)
committerGitHub <redacted>
Tue, 12 May 2026 20:10:37 +0000 (13:10 -0700)
commita9883db8ee021cf16783016a60996d41820b5195
tree6bc4a911e6a48f85a8f7579775de9cb91b39a1bftree
parentcce09f0b2b37028caf6f549c976ba16b3e8703d8commit | diff
opencl: add opt-in Adreno xmem F16xF32 GEMM for prefill (#22755)

* ggml-opencl: add Adreno xmem F16xF32 GEMM for prefill

* ggml-opencl: address Adreno xmem review comments

* ggml-opencl: align xmem gemm kernel naming

---------

Co-authored-by: Your Name <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/gemm_xmem_f16_f32_os8.cl [new file with mode: 0644] blob
Packaging of ggml-org/llama.cpp