]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 8da3c0e)
CUDA: add expert reduce kernel (#16857)
authorAman Gupta <redacted>
Fri, 31 Oct 2025 12:05:07 +0000 (20:05 +0800)
committerGitHub <redacted>
Fri, 31 Oct 2025 12:05:07 +0000 (20:05 +0800)
commit4146d6a1a6228711a487a1e3e9ddd120f8d027d7
treebde41ac4448629122097264a9e741b7816877be7tree
parent8da3c0e200a586f768ada6f38745acb01380174ccommit | diff
CUDA: add expert reduce kernel (#16857)

* CUDA: add expert reduce kernel

* contigous checks, better formatting, use std::vector instead of array

* use vector empty instead of size

Co-authored-by: Johannes Gäßler <redacted>
---------

Co-authored-by: Johannes Gäßler <redacted>
ggml/src/ggml-cuda/ggml-cuda.cu diff | blob | history
ggml/src/ggml-cuda/moe-expert-reduce.cu [new file with mode: 0644] blob
ggml/src/ggml-cuda/moe-expert-reduce.cuh [new file with mode: 0644] blob
tests/test-backend-ops.cpp diff | blob | history
Packaging of ggml-org/llama.cpp