]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 1b01f06)
ggml: implement quantized KV cache for FA (#7372)
authorJohannes Gäßler <redacted>
Sun, 19 May 2024 14:46:13 +0000 (16:46 +0200)
committerGitHub <redacted>
Sun, 19 May 2024 14:46:13 +0000 (16:46 +0200)
commit5ca49cbecda27ce0a7266658fc3b640bff3ed386
tree78dd422c1199292550963287954a26ca0a11ee59tree
parent1b01f06db0cff5f5f600bb754fc39fde565ed56acommit | diff
ggml: implement quantized KV cache for FA (#7372)
ggml.c diff | blob | history
Packaging of ggml-org/llama.cpp