]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 3323112)
CUDA: faster k-quant mul_mat_q kernels (#2525)
authorJohannes Gäßler <redacted>
Sat, 5 Aug 2023 16:20:44 +0000 (18:20 +0200)
committerGitHub <redacted>
Sat, 5 Aug 2023 16:20:44 +0000 (18:20 +0200)
commitf514d1b306e1114c2884fcb25dd9bd48ae64ba32
tree854ca044bf124a08026afcbb6c03c7d6c617736dtree
parent332311234a0aa2974b2450710e22e09d90dd6b0bcommit | diff
CUDA: faster k-quant mul_mat_q kernels (#2525)
ggml-cuda.cu diff | blob | history
Packaging of ggml-org/llama.cpp