 Xuan-Son Nguyen
|
be7c303410
arg : no n_predict = -2 for examples except for main and infill (#12364)
|
10 ماه پیش |
 marcoStocchi
|
6ef79a67ca
common : refactor '-o' option (#12278)
|
10 ماه پیش |
 Georgi Gerganov
|
1e2f78a004
server : add speculative decoding presets for FIM (#12287)
|
10 ماه پیش |
 Sigbjørn Skjæret
|
56d7a9f812
main: allow preloading conversation with -p and add -st / --single-turn (#12145)
|
10 ماه پیش |
 dm4
|
c43af9276b
tts: add speaker file support (#12048)
|
10 ماه پیش |
|
Sigbjørn Skjæret
|
45a8e76745
common : add --system-prompt parameter, replace behavior of -p in conversation mode (#12131)
|
10 ماه پیش |
 Daniel Bevenius
|
d07c621393
common : add llama.vim preset for Qwen2.5 Coder (#11945)
|
11 ماه پیش |
 Olivier Chafik
|
63e489c025
tool-call: refactor common chat / tool-call api (+ tests / fixes) (#11900)
|
11 ماه پیش |
 standby24x7
|
fe163d5bf3
common : Fix a typo in help (#11899)
|
11 ماه پیش |
|
Georgi Gerganov
|
68ff663a04
repo : update links to new url (#11886)
|
11 ماه پیش |
|
Daniel Bevenius
|
3d68f034da
llama : add completion for --chat-template-file (#11860)
|
11 ماه پیش |
|
Daniel Bevenius
|
c48f630d1c
llama : add --completion-bash option (#11846)
|
11 ماه پیش |
|
Olivier Chafik
|
c7f460ab88
`server`: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless `--reasoning-format none` (#11607)
|
11 ماه پیش |
 Vinesh Janarthanan
|
27e8a23300
sampling: add Top-nσ sampler (#11223)
|
11 ماه پیش |
 Maxim Evtush
|
7b891bdc86
fix: typos in documentation files (#11791)
|
11 ماه پیش |
|
Daniel Bevenius
|
b7552cfcbc
common : add default embeddings presets (#11677)
|
11 ماه پیش |
 Radoslav Gerganov
|
1bef571f6a
arg : list RPC devices first when using --list-devices (#11655)
|
11 ماه پیش |
|
Daniel Bevenius
|
b636228c0a
embedding : enable --no-warmup option (#11475)
|
11 ماه پیش |
|
Olivier Chafik
|
6171c9d258
Add Jinja template support (#11016)
|
1 سال پیش |
|
Georgi Gerganov
|
80d0d6b4b7
common : add -hfd option for the draft model (#11318)
|
1 سال پیش |
 LostRuins Concedo
|
6390a998bf
tts : add guide tokens support (#11186)
|
1 سال پیش |
|
Radoslav Gerganov
|
667d72846c
rpc : early register backend devices (#11262)
|
1 سال پیش |
 Xuan Son Nguyen
|
84a44815f7
cli : auto activate conversation mode if chat template is available (#11214)
|
1 سال پیش |
|
Xuan Son Nguyen
|
00b4c3da62
common : support tag-based --hf-repo like on ollama (#11195)
|
1 سال پیش |
|
Georgi Gerganov
|
a3c1232c3f
arg : option to exclude arguments from specific examples (#11136)
|
1 سال پیش |
|
Georgi Gerganov
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
1 سال پیش |
 Molly Sophia
|
0a11f8b7b5
convert : fix RWKV v6 model conversion (#10913)
|
1 سال پیش |
|
Georgi Gerganov
|
36319dec5d
tts : small QoL for easy model fetch (#10903)
|
1 سال پیش |
|
Georgi Gerganov
|
0bf2d10c55
tts : add OuteTTS support (#10784)
|
1 سال پیش |
|
Georgi Gerganov
|
644fd71b44
sampling : refactor + optimize penalties sampler (#10803)
|
1 سال پیش |
