]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 0a4a4a0)
llama : quantize up to 31% faster on Linux and Windows with mmap (#3206)
authorCebtenzzre <redacted>
Fri, 29 Sep 2023 13:48:45 +0000 (09:48 -0400)
committerGitHub <redacted>
Fri, 29 Sep 2023 13:48:45 +0000 (16:48 +0300)
commit2777a84be429401a2b7d33c2b6a4ada1f0776f1b
tree27d6f6a382d4987584f6c6ad2648a901ea00b144tree
parent0a4a4a098261ddd26480371eaccfe90d1bf6488acommit | diff
llama : quantize up to 31% faster on Linux and Windows with mmap (#3206)

* llama : enable mmap in quantize on Linux -> 31% faster

* also enable mmap on Windows

---------

Co-authored-by: Georgi Gerganov <redacted>
llama.cpp diff | blob | history
Packaging of ggml-org/llama.cpp