Releases: tterrasson/llama.cpp
Releases · tterrasson/llama.cpp
b2611
b1564
llama : grammar `reserve` space in `decode_utf8` (#4210) * reserve space for codepoints * improvement for the appended 0
b1448
samplers : Min-P sampler implementation [alternative to Top P/Top K] … …(#3841) * Introduce the new Min-P sampler by @kalomaze The Min-P sampling method was designed as an alternative to Top-P, and aims to ensure a balance of quality and variety. The parameter *p* represents the minimum probability for a token to be considered, relative to the probability of the most likely token. * Min-P enabled and set to 0.05 default --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: cebtenzzre <cebtenzzre@gmail.com>
b1433
Merge branch 'ggerganov:master' into master
b1430
simple : fix batch handling
b1429
server : do not release slot on image input (#3798)