]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: e8035f1)
cuda : allocate all temporary ggml_tensor_extra_gpu from a fixed-size buffer (#2220)
authorBach Le <redacted>
Fri, 14 Jul 2023 19:00:58 +0000 (03:00 +0800)
committerGitHub <redacted>
Fri, 14 Jul 2023 19:00:58 +0000 (22:00 +0300)
commit7cdd30bf1f84339c55a5e3de29384f6bbdebb61c
treebb1c862aebba80b175f213246da5ea771d62da17tree
parente8035f141e1f71d739fa5cfc9c01531cdee6fc16commit | diff
cuda : allocate all temporary ggml_tensor_extra_gpu from a fixed-size buffer (#2220)
ggml-cuda.cu diff | blob | history
Packaging of ggml-org/llama.cpp