cturan/llama.cpp

mirror da https://github.com/cturan/llama.cpp

Autore	SHA1 Messaggio	Data
Faisal Zaghloul	42c76d1358 Threadpool: take 2 (#8672)	1 anno fa
Clint Herron	07a3fc0608 Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258)	1 anno fa
Georgi Gerganov	2b3389677a ggml : refactor rope norm/neox (#7634)	1 anno fa
Georgi Gerganov	ec893798b7 llama : custom attention mask + parallel decoding + no context swaps (#3228)	2 anni fa