 Georgi Gerganov
|
abd4d0bc4f
speculative : update default params (#11954)
|
hai 11 meses |
 Olivier Chafik
|
63e489c025
tool-call: refactor common chat / tool-call api (+ tests / fixes) (#11900)
|
hai 11 meses |
 Daniel Bevenius
|
c48f630d1c
llama : add --completion-bash option (#11846)
|
hai 11 meses |
|
Olivier Chafik
|
c7f460ab88
`server`: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless `--reasoning-format none` (#11607)
|
hai 11 meses |
 Vinesh Janarthanan
|
27e8a23300
sampling: add Top-nσ sampler (#11223)
|
hai 11 meses |
 bandoti
|
fef0cbeadf
cleanup: fix compile warnings associated with gnu_printf (#11811)
|
hai 11 meses |
|
Olivier Chafik
|
bfcce4d693
`tool-call`: support Command R7B (+ return tool_plan "thoughts" in API) (#11585)
|
hai 11 meses |
|
Olivier Chafik
|
8b576b6c55
Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars (#9639)
|
hai 11 meses |
|
Olivier Chafik
|
a94f3b2727
`common`: utils to split / join / repeat strings (from json converter) (#11342)
|
hai 1 ano |
|
Olivier Chafik
|
6171c9d258
Add Jinja template support (#11016)
|
hai 1 ano |
|
Georgi Gerganov
|
80d0d6b4b7
common : add -hfd option for the draft model (#11318)
|
hai 1 ano |
 LostRuins Concedo
|
6390a998bf
tts : add guide tokens support (#11186)
|
hai 1 ano |
 Radoslav Gerganov
|
667d72846c
rpc : early register backend devices (#11262)
|
hai 1 ano |
 Xuan Son Nguyen
|
84a44815f7
cli : auto activate conversation mode if chat template is available (#11214)
|
hai 1 ano |
|
Xuan Son Nguyen
|
00b4c3da62
common : support tag-based --hf-repo like on ollama (#11195)
|
hai 1 ano |
|
Georgi Gerganov
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
hai 1 ano |
|
Georgi Gerganov
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
hai 1 ano |
|
Xuan Son Nguyen
|
45095a61bf
server : clean up built-in template detection (#11026)
|
hai 1 ano |
|
Georgi Gerganov
|
0bf2d10c55
tts : add OuteTTS support (#10784)
|
hai 1 ano |
|
Georgi Gerganov
|
152610eda9
server : output embeddings for all tokens when pooling = none (#10861)
|
hai 1 ano |
|
Georgi Gerganov
|
644fd71b44
sampling : refactor + optimize penalties sampler (#10803)
|
hai 1 ano |
 Eric Curtin
|
c27ac678dd
Opt class for positional argument handling (#10508)
|
hai 1 ano |
|
Xuan Son Nguyen
|
adffa6ffd5
common : improve -ctv -ctk CLI arguments (#10806)
|
hai 1 ano |
|
Xuan Son Nguyen
|
6c5bc0625f
server : (refactoring) do not rely on JSON internally (#10643)
|
hai 1 ano |
 haopeng
|
64ed2091b2
server: Add "tokens per second" information in the backend (#10548)
|
hai 1 ano |
|
Xuan Son Nguyen
|
9f912511bc
common : fix duplicated file name with hf_repo and hf_file (#10550)
|
hai 1 ano |
 Diego Devesa
|
10bce0450f
llama : accept a list of devices to use to offload a model (#10497)
|
hai 1 ano |
|
Georgi Gerganov
|
d9d54e498d
speculative : refactor and add a simpler example (#10362)
|
hai 1 ano |
 Johannes Gäßler
|
4e54be0ec6
llama/ex: remove --logdir argument (#10339)
|
hai 1 ano |
|
Georgi Gerganov
|
b141e5f6ef
server : enable KV cache defrag by default (#10233)
|
hai 1 ano |
