]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: d54a402)
CUDA: fix mul_mat_q not used for output tensor (#3127)
authorJohannes Gäßler <redacted>
Mon, 11 Sep 2023 20:58:41 +0000 (22:58 +0200)
committerGitHub <redacted>
Mon, 11 Sep 2023 20:58:41 +0000 (22:58 +0200)
commit89e89599fd095172f8d67903b5e227467420f036
tree8628a31b9b91b0affdc1e5ff60eab7fe5c610497tree
parentd54a4027a6ebda98ab0fef7fa0c2247d0bef132acommit | diff
CUDA: fix mul_mat_q not used for output tensor (#3127)
ggml-cuda.cu diff | blob | history
Packaging of ggml-org/llama.cpp