COMMITS
/ include/llama.h December 11, 2024
K
bug-fix: snprintf prints NULL in place of the last character (#10419)
kallewoof committed
December 7, 2024
D
ggml : refactor online repacking (#10446)
Djip007 committed
December 5, 2024
R
llama : add Minerva 7B model support (#10673)
Riccardo Orlando committed
December 4, 2024
J
llama: Support MiniCPM-1B (with & w/o longrope) (#10559)
JFLFY2255 committed
December 3, 2024
X
llama : add missing LLAMA_API for llama_chat_builtin_templates (#10636)
Xuan Son Nguyen committed
December 2, 2024
X
llama : add enum for built-in chat templates (#10623)
Xuan Son Nguyen committed
November 25, 2024
D
llama : accept a list of devices to use to offload a model (#10497)
Diego Devesa committed
November 19, 2024
G
llama : add check for KV cache shifts (#10401)
Georgi Gerganov committed
November 16, 2024
J
llama/ex: remove --logdir argument (#10339)
Johannes Gäßler committed
November 13, 2024
M
llama : propagate the results of `graph_compute` (#9525)
Michael Podvitskiy committed
November 3, 2024
D
ggml : move CPU backend to a separate file (#10144)
Diego Devesa committed
October 30, 2024
D
llama : refactor model loader with backend registry (#10026)
Diego Devesa committed
October 29, 2024
G
llama : remove Tail-Free sampling (#10071)
Georgi Gerganov committed
October 25, 2024
W
llama : add DRY sampler (#9702)
wwoodsTM committed
October 21, 2024
G
llama : default sampling changes + greedy update (#9897)
Georgi Gerganov 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 17, 2024
G
llama : infill sampling handle very long tokens (#9924)
Georgi Gerganov committed
October 15, 2024
G
llama : add infill sampler (#9896)
Georgi Gerganov committed
M
sampling : add XTC sampler (#9742)
MaggotHATE committed
October 12, 2024
G
llama : improve infill support and special token detection (#9798)
Georgi Gerganov committed
October 10, 2024
D
rpc : add backend registry / device interfaces (#9812)
Diego Devesa committed
September 28, 2024
G
llama : add reranking support (#9510)
Georgi Gerganov committed
G
llama : add comment about thread-safety [no ci] (#9449)
Georgi Gerganov committed
N
llama : add support for Chameleon (#8543)
nopperl committed
September 24, 2024
G
sampling : avoid expensive softmax during greedy sampling (#9605)
Georgi Gerganov committed
September 17, 2024
M
llama : add llama_n_head() (#9512)
Michael Podvitskiy committed
September 13, 2024
G
llama : llama_perf + option to disable timings during decode (#9355)
Georgi Gerganov committed
G
feat: remove a sampler from a chain (#9445)
Gilad S. committed
September 10, 2024
S
llama : move random seed generation to the samplers (#9398)
slaren committed
September 9, 2024
S
llama : minor sampling refactor (2) (#9386)
slaren committed
September 7, 2024
G
llama : refactor sampling v2 (#9294)
Georgi Gerganov committed
September 6, 2024
C
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)
compilade committed
September 1, 2024
M
llama : support RWKV v6 models (#8980)
Molly Sophia committed
August 30, 2024
S
llama : fix llama_split_mode enum values in main_gpu document (#9057)
Sutou Kouhei committed
August 29, 2024
F
Threadpool: take 2 (#8672)
Faisal Zaghloul committed
August 21, 2024
C
llama : simplify Mamba with advanced batch splits (#8526)
compilade committed
August 16, 2024
M
llama : add EXAONE model support (#9025)
Minsoo Cheong committed
August 15, 2024
Z
common : remove duplicate function llama_should_add_bos_token (#8778)
Zhenwei Jin committed
E
llama : add pre-tokenizer regexes for BLOOM and gpt3-finnish (#8850)
Esko Toivonen committed
August 13, 2024
D
ggml : move rope type enum to ggml.h (#8949)
Daniel Bevenius committed
August 10, 2024
F
Add support for encoder-only T5 models (#8900)
fairydreaming committed
August 6, 2024
N
typo correction (#8891)
Nexes the Old committed
July 28, 2024
C
llama : refactor session file management (#8699)
compilade committed
July 24, 2024
X
add llama_lora_adapter_clear (#8653)
Xuan Son Nguyen committed
July 23, 2024
G
llama : move vocab, grammar and sampling into separate files (#8508)
Georgi Gerganov committed
July 22, 2024
K
llama : fix codeshell support (#8599)
Keke Han committed
J
llama : add support for SmolLm pre-tokenizer (#8609)
Jason Stillerman committed
July 20, 2024
M
llama : add support for Tekken pre-tokenizer (#8579)
Michael Coppola committed
July 19, 2024
G
llama : bump max layers from 256 to 512 (#8530)
Georgi Gerganov committed
July 16, 2024
G
llama : valign + remove unused ftype (#8502)
Georgi Gerganov committed