]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: f5bfea0)
CUDA: tuned mul_mat_q kernels (#2546)
authorJohannes Gäßler <redacted>
Wed, 9 Aug 2023 07:42:34 +0000 (09:42 +0200)
committerGitHub <redacted>
Wed, 9 Aug 2023 07:42:34 +0000 (09:42 +0200)
commit25d43e0eb578b6e73046d9d6644a3a14d460600d
treefddb8e9a044ce7eda09024e345a871cdada4cac8tree
parentf5bfea0580e417f99850d5456ca541d871a3e48ccommit | diff
CUDA: tuned mul_mat_q kernels (#2546)
Makefile diff | blob | history
README.md diff | blob | history
ggml-cuda.cu diff | blob | history
Packaging of ggml-org/llama.cpp