]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: cb13ef8)
CUDA: faster non-contiguous concat (#10760)
authora3sh <redacted>
Thu, 12 Dec 2024 18:09:50 +0000 (02:09 +0800)
committerGitHub <redacted>
Thu, 12 Dec 2024 18:09:50 +0000 (19:09 +0100)
commit8faa1d4dd42f6cb26088ce7f5bbca5996b921685
tree126a46a096ee0c860b3e551c5a2f5099e633bc22tree
parentcb13ef85a444eb52a3f1b82dce198ceb25606583commit | diff
CUDA: faster non-contiguous concat (#10760)

* faster uncontiguous concat

* Use a lambda to avoid code duplication

Co-authored-by: Diego Devesa <redacted>
* Update ggml/src/ggml-cuda/concat.cu

* add constexpr  and static assert

---------

Co-authored-by: Diego Devesa <redacted>
ggml/src/ggml-cuda/concat.cu diff | blob | history
Packaging of ggml-org/llama.cpp