 Isaac McFadyen
|
6a2bc8bfb7
server : added --no-prefill-assistant flag (#13608)
|
8 месяцев назад |
 Olivier Chafik
|
3198405e98
`common`: add partial regex support (#12808)
|
8 месяцев назад |
 Johannes Gäßler
|
10d2af0eaa
llama/ggml: add LLM training support (#10544)
|
8 месяцев назад |
 David Huang
|
7f323a589f
Add `--no-op-offload` to improve `-ot` pp perf in MoE models like llama4 400B (#13386)
|
8 месяцев назад |
 Bartowski
|
efb8b47eda
imatrix : Add --parse-special for enabling parsing of special tokens in imatrix calculation (#13389)
|
8 месяцев назад |
 Georgi Gerganov
|
51fb96b1ff
context : remove logits_all flag (#13284)
|
8 месяцев назад |
|
Georgi Gerganov
|
4773d7a02f
examples : remove infill (#13283)
|
8 месяцев назад |
 oobabooga
|
233461f812
sampling : Integrate Top-nσ into main sampling chain (and add it to the server) (#13264)
|
8 месяцев назад |
 Xuan-Son Nguyen
|
9b61acf060
mtmd : rename llava directory to mtmd (#13311)
|
8 месяцев назад |
 Diego Devesa
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
8 месяцев назад |
|
Xuan-Son Nguyen
|
7c727fbe39
arg : add --no-mmproj-offload (#13093)
|
8 месяцев назад |
|
Xuan-Son Nguyen
|
80982e815e
arg : clean up handling --mmproj with -hf (#13082)
|
8 месяцев назад |
 tastelikefeet
|
b2034c2b55
contrib: support modelscope community (#12664)
|
9 месяцев назад |
|
Diego Devesa
|
e0e912f49b
llama : add option to override model tensor buffers (#11397)
|
9 месяцев назад |
|
Xuan-Son Nguyen
|
42eb248f46
common : remove json.hpp from common.cpp (#12697)
|
9 месяцев назад |
|
Xuan-Son Nguyen
|
267c1399f1
common : refactor downloading system, handle mmproj with -hf option (#12694)
|
9 месяцев назад |
 marcoStocchi
|
6ef79a67ca
common : refactor '-o' option (#12278)
|
10 месяцев назад |
|
Olivier Chafik
|
669912d9a5
`tool-call`: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034)
|
10 месяцев назад |
 Sigbjørn Skjæret
|
56d7a9f812
main: allow preloading conversation with -p and add -st / --single-turn (#12145)
|
10 месяцев назад |
 dm4
|
c43af9276b
tts: add speaker file support (#12048)
|
10 месяцев назад |
|
Sigbjørn Skjæret
|
45a8e76745
common : add --system-prompt parameter, replace behavior of -p in conversation mode (#12131)
|
10 месяцев назад |
|
Georgi Gerganov
|
abd4d0bc4f
speculative : update default params (#11954)
|
11 месяцев назад |
|
Olivier Chafik
|
63e489c025
tool-call: refactor common chat / tool-call api (+ tests / fixes) (#11900)
|
11 месяцев назад |
 Daniel Bevenius
|
c48f630d1c
llama : add --completion-bash option (#11846)
|
11 месяцев назад |
|
Olivier Chafik
|
c7f460ab88
`server`: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless `--reasoning-format none` (#11607)
|
11 месяцев назад |
 Vinesh Janarthanan
|
27e8a23300
sampling: add Top-nσ sampler (#11223)
|
11 месяцев назад |
 bandoti
|
fef0cbeadf
cleanup: fix compile warnings associated with gnu_printf (#11811)
|
11 месяцев назад |
|
Olivier Chafik
|
bfcce4d693
`tool-call`: support Command R7B (+ return tool_plan "thoughts" in API) (#11585)
|
11 месяцев назад |
|
Olivier Chafik
|
8b576b6c55
Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars (#9639)
|
11 месяцев назад |
|
Olivier Chafik
|
a94f3b2727
`common`: utils to split / join / repeat strings (from json converter) (#11342)
|
1 год назад |
