]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 160bfb2)
Command line switch to use F16 for memory_k and memory_v (refactor of #154) (#294)
authorErik Scholz <redacted>
Sun, 19 Mar 2023 17:57:00 +0000 (18:57 +0100)
committerGitHub <redacted>
Sun, 19 Mar 2023 17:57:00 +0000 (19:57 +0200)
commit0b366e735729327476ec31da02de3c9c9771ddfb
tree84022e2ae4d512f44e430a0fb8b49acf3c4a6f72tree
parent160bfb217da5038ccbd74438f9f16a16012d7866commit | diff
Command line switch to use F16 for memory_k and memory_v (refactor of #154) (#294)

* Use F16 for memory_k and memory_v

* add command line switch to use f16 instead of f32 for memory k+v

---------

Co-authored-by: Ty Everett <redacted>
main.cpp diff | blob | history
utils.cpp diff | blob | history
utils.h diff | blob | history
Packaging of ggml-org/llama.cpp