]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
Reduce model loading time (#43)
authoruint256_t <redacted>
Mon, 13 Mar 2023 16:33:43 +0000 (01:33 +0900)
committerGitHub <redacted>
Mon, 13 Mar 2023 16:33:43 +0000 (18:33 +0200)
commit63fd76fbb06f9b723ca11505352387a3148b1814
tree10e4d2c002837c522339ecc2a6742b5ea9bcd0a3
parent2a20f48efad692a8c2744f10c673bbdbe0c751b7
Reduce model loading time (#43)

* Use buffering

* Use vector

* Minor

---------

Co-authored-by: Georgi Gerganov <redacted>
main.cpp