cturan/llama.cpp

огледало од https://github.com/cturan/llama.cpp

Аутор	SHA1 Порука	Датум
Georgi Gerganov	dd665cc9d4 parallel : increase the variability of the prompt lengths (#13927)	пре 7 месеци
Georgi Gerganov	518329b2d4 parallel : add option for non-shared and larger prompts (#13598)	пре 8 месеци
Richard Kiss	532dd74e38 Fix some documentation typos/grammar mistakes (#4032)	пре 2 година
Georgi Gerganov	ec893798b7 llama : custom attention mask + parallel decoding + no context swaps (#3228)	пре 2 година