]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: c2ce6c4)
CUDA: int8 tensor cores for MMQ (q4_K, q5_K, q6_K) (#7860)
authorJohannes Gäßler <redacted>
Tue, 11 Jun 2024 06:26:07 +0000 (08:26 +0200)
committerGitHub <redacted>
Tue, 11 Jun 2024 06:26:07 +0000 (08:26 +0200)
commitbdcb8f42221bc40c411150a009a3d3a30fa74722
tree4009cbabbbcb7a022ad1df8233726aee8dc8d65btree
parentc2ce6c47e4f2d891bf29d8810832a3b310a8f205commit | diff
CUDA: int8 tensor cores for MMQ (q4_K, q5_K, q6_K) (#7860)
ggml-cuda/mma.cuh diff | blob | history
ggml-cuda/mmq.cuh diff | blob | history
Packaging of ggml-org/llama.cpp