 Olivier Chafik
|
8b576b6c55
Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars (#9639)
|
11 months ago |
|
Olivier Chafik
|
6171c9d258
Add Jinja template support (#11016)
|
1 year ago |
 Radoslav Gerganov
|
667d72846c
rpc : early register backend devices (#11262)
|
1 year ago |
 David Renshaw
|
960ec65273
llama : fix deprecation message: vocabable -> vocab (#11269)
|
1 year ago |
 Xuan Son Nguyen
|
681149ced2
llama : add `llama_model_load_from_splits` (#11255)
|
1 year ago |
 Georgi Gerganov
|
08f10f69c3
llama : remove notion of CLS token (#11064)
|
1 year ago |
|
Georgi Gerganov
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
1 year ago |
|
Georgi Gerganov
|
47182dd03f
llama : update llama_model API names (#11063)
|
1 year ago |
|
Georgi Gerganov
|
727368c60f
llama : use LLAMA_TOKEN_NULL (#11062)
|
1 year ago |
 fairydreaming
|
9394bbd484
llama : Add support for DeepSeek V3 (#11049)
|
1 year ago |
|
Georgi Gerganov
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
1 year ago |
|
Georgi Gerganov
|
0bf2d10c55
tts : add OuteTTS support (#10784)
|
1 year ago |
|
Georgi Gerganov
|
644fd71b44
sampling : refactor + optimize penalties sampler (#10803)
|
1 year ago |
 HimariO
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
1 year ago |
 kallewoof
|
484d2f31ae
bug-fix: snprintf prints NULL in place of the last character (#10419)
|
1 year ago |
 Djip007
|
19d8762ab6
ggml : refactor online repacking (#10446)
|
1 year ago |
 Riccardo Orlando
|
6fe6247831
llama : add Minerva 7B model support (#10673)
|
1 year ago |
 JFLFY2255
|
8d0cfd554a
llama: Support MiniCPM-1B (with & w/o longrope) (#10559)
|
1 year ago |
|
Xuan Son Nguyen
|
3b4f2e33e2
llama : add missing LLAMA_API for llama_chat_builtin_templates (#10636)
|
1 year ago |
|
Xuan Son Nguyen
|
642330ac7c
llama : add enum for built-in chat templates (#10623)
|
1 year ago |
 Diego Devesa
|
10bce0450f
llama : accept a list of devices to use to offload a model (#10497)
|
1 year ago |
|
Georgi Gerganov
|
8e752a777b
llama : add check for KV cache shifts (#10401)
|
1 year ago |
 Johannes Gäßler
|
4e54be0ec6
llama/ex: remove --logdir argument (#10339)
|
1 year ago |
 Michael Podvitskiy
|
fb4a0ec083
llama : propagate the results of `graph_compute` (#9525)
|
1 year ago |
|
Diego Devesa
|
9f40989351
ggml : move CPU backend to a separate file (#10144)
|
1 year ago |
|
Diego Devesa
|
c5b0f4b5d9
llama : refactor model loader with backend registry (#10026)
|
1 year ago |
|
Georgi Gerganov
|
8d8ff71536
llama : remove Tail-Free sampling (#10071)
|
1 year ago |
 wwoodsTM
|
ff252ea48e
llama : add DRY sampler (#9702)
|
1 year ago |
|
Georgi Gerganov
|
55e47786e3
llama : default sampling changes + greedy update (#9897)
|
1 year ago |
|
Xuan Son Nguyen
|
cda0e4b648
llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)
|
1 year ago |
