]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 7ed8d1f)
CUDA: tighter VRAM scratch size for 65b/70b (#2551)
authorJohannes Gäßler <redacted>
Tue, 8 Aug 2023 12:38:16 +0000 (14:38 +0200)
committerGitHub <redacted>
Tue, 8 Aug 2023 12:38:16 +0000 (14:38 +0200)
commitacfc5478ff3446ca3b54553967a3dea09b7c771a
treeaa8fd4955191bb4374e67906a5c3fe7cefb8bc25tree
parent7ed8d1fe7f8cbe6a6763e6b46759795ac8d21e12commit | diff
CUDA: tighter VRAM scratch size for 65b/70b (#2551)
llama.cpp diff | blob | history
Packaging of ggml-org/llama.cpp