]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: dfd9b5f)
CUDA: MoE helper in device code, better tile sizes (#15525)
authorJohannes Gäßler <redacted>
Mon, 25 Aug 2025 15:23:40 +0000 (17:23 +0200)
committerGitHub <redacted>
Mon, 25 Aug 2025 15:23:40 +0000 (17:23 +0200)
commit5eff6ec9b1220b599a43b594b1110487ab6aca08
tree76dce20cd38c8435f40eadf2933b63437c2d6215tree
parentdfd9b5f6c7586c88588f06a644c131bec071a0a1commit | diff
CUDA: MoE helper in device code, better tile sizes (#15525)

* CUDA: MoE helper in device code, better tile sizes

* reduce superfluous CUDA blocks
ggml/src/ggml-cuda/common.cuh diff | blob | history
ggml/src/ggml-cuda/mmq.cu diff | blob | history
ggml/src/ggml-cuda/mmq.cuh diff | blob | history
ggml/src/ggml-cuda/vendors/hip.h diff | blob | history
Packaging of ggml-org/llama.cpp