]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 4f6b60c)
CUDA: faster non k-quant mul_mat_q kernels (#2483)
authorJohannes Gäßler <redacted>
Wed, 2 Aug 2023 16:04:04 +0000 (18:04 +0200)
committerGitHub <redacted>
Wed, 2 Aug 2023 16:04:04 +0000 (18:04 +0200)
commit468ea24fb4633a0d681f7ac84089566c1c6190cb
tree95a9bd9234539e9e8caa97f8a3e040265faac34btree
parent4f6b60c77652cdfc9d5545fe247ae5d764815598commit | diff
CUDA: faster non k-quant mul_mat_q kernels (#2483)
ggml-cuda.cu diff | blob | history
Packaging of ggml-org/llama.cpp