COMMITS
/ examples/main/main.cpp November 25, 2024
D
ggml : add support for dynamic loading of backends (#10469)
Diego Devesa committed
G
speculative : refactor and add a simpler example (#10362)
Georgi Gerganov committed
November 16, 2024
J
llama/ex: remove --logdir argument (#10339)
Johannes Gäßler committed
October 18, 2024
X
llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)
Xuan Son Nguyen committed
October 15, 2024
G
llama : add infill sampler (#9896)
Georgi Gerganov committed
October 10, 2024
D
common : use common_ prefix for common library functions (#9805)
Diego Devesa committed
September 24, 2024
G
log : add CONT level for continuing previous log entry (#9610)
Georgi Gerganov committed
September 20, 2024
G
examples : flush log upon ctrl+c (#9559)
Georgi Gerganov committed
September 16, 2024
V
main : option to disable context shift (#9484)
Vinesh Janarthanan committed
September 15, 2024
G
common : reimplement logging (#9418)
Georgi Gerganov committed
September 10, 2024
S
llama : move random seed generation to the samplers (#9398)
slaren committed
September 9, 2024
X
common : move arg parser code to `arg.cpp` (#9388)
Xuan Son Nguyen committed
September 7, 2024
X
common : refactor arg parser (#9308)
Xuan Son Nguyen committed
G
llama : refactor sampling v2 (#9294)
Georgi Gerganov committed
September 2, 2024
G
llama-cli : remove duplicated log message (#9275)
Guoliang Hua committed
August 29, 2024
F
Threadpool: take 2 (#8672)
Faisal Zaghloul committed
August 15, 2024
Z
common : remove duplicate function llama_should_add_bos_token (#8778)
Zhenwei Jin committed
August 5, 2024
L
common : Changed tuple to struct (TODO fix) (#8823)
Liu Jia committed
July 24, 2024
X
llama : fix `llama_chat_format_single` for mistral (#8657)
Xuan Son Nguyen committed
July 12, 2024
G
main : print error on empty input (#8456)
Georgi Gerganov committed
July 4, 2024
X
cli: add EOT when user hit Ctrl+C (#8296)
Xuan Son Nguyen committed
F
Inference support for T5 and FLAN-T5 model families (#5763)
fairydreaming committed
June 30, 2024
X
Fix new line issue with chat template, disable template when in-prefix/suffix is set (#8203)
Xuan Son Nguyen committed
June 28, 2024
X
fix code typo in llama-cli (#8198)
Xuan Son Nguyen committed
June 25, 2024
X
Add chat template support for llama-cli (#8068)
Xuan Son Nguyen committed
June 4, 2024
G
common : refactor cli arg parsing (#7675)
Georgi Gerganov committed
May 26, 2024
B
main: replace --no-special with --special (#7534)
Brian committed
May 25, 2024
J
main : don't print special tokens with --grammar (#6923)
Justine Tunney committed
May 23, 2024
G
main : minor (#7462)
Georgi Gerganov committed
May 22, 2024
G
common : normalize naming style (#7462)
Georgi Gerganov committed
May 21, 2024
O
`grammars`: fix resampling logic regression (#7424)
Olivier Chafik committed
May 10, 2024
J
Fix memory bug in grammar parser (#7194)
Justine Tunney committed
H
Main+: optionally allow special tokens from user in interactive mode (#7097)
HanishKVC committed
May 8, 2024
D
main : add --conversation / -cnv flag (#7108)
Dawid Potocki committed
May 7, 2024
R
main : update log text (EOS to EOG) (#7104)
RhinoDevel committed
May 1, 2024
L
main : fix off by one error for context shift (#6921)
l3utterfly committed
April 29, 2024
D
main : fix typo in comment in main.cpp (#6985)
Daniel Bevenius committed
April 24, 2024
J
Server: fix seed for multiple slots (#6835)
Johannes Gäßler committed
April 21, 2024
P
llama : support Llama 3 HF conversion (#6745)
Pedro Cuenca committed
April 9, 2024
J
BERT tokenizer fixes (#6498)
Jared Van Bortel committed
April 8, 2024
J
llama : save and restore kv cache for single seq id (#6341)
Jan Boon committed
March 11, 2024
G
llama : more consistent names of count variables (#5994)
Georgi Gerganov committed
March 4, 2024
D
main : support special tokens as reverse/anti prompt (#5847)
DAN™ committed
February 25, 2024
G
llama : refactor k-shift implementation + KV defragmentation (#5691)
Georgi Gerganov committed
February 21, 2024
J
examples : do not assume BOS when shifting context (#5622)
Jared Van Bortel committed
February 16, 2024
B
ggml : add numa options (#5377)
bmwl committed
February 11, 2024
G
main : ctrl+C print timing in non-interactive mode (#3873)
Georgi Gerganov committed
February 3, 2024
M
refactor : switch to emplace_back to avoid extra object (#5291)
Michael Klimenko committed
January 30, 2024
D
main : allow empty --prompt-cache file (#5176)
divinity76 committed
January 13, 2024
Y
main : add parameter --no-display-prompt (#4541)
Yann Follet committed