 Xuan-Son Nguyen
|
10961339b2
mtmd : move helpers to dedicated library (⚠️ breaking change) (#13866)
|
пре 7 месеци |
 Olivier Chafik
|
03f582ae8f
server: fix streaming crashes (#13786)
|
пре 7 месеци |
 Georgi Gerganov
|
79c137f776
examples : allow extracting embeddings from decoder contexts (#13797)
|
пре 7 месеци |
|
Olivier Chafik
|
e121edc432
`server`: add `--reasoning-budget 0` to disable thinking (incl. qwen3 w/ enable_thinking:false) (#13771)
|
пре 7 месеци |
|
Olivier Chafik
|
f5cd27b71d
`server`: streaming of tool calls and thoughts when `--jinja` is on (#12379)
|
пре 7 месеци |
|
Xuan-Son Nguyen
|
9ecf3e66a3
server : support audio input (#13714)
|
пре 7 месеци |
|
Georgi Gerganov
|
cc74d5be99
server : pad small embedding batches (#13692)
|
пре 8 месеци |
|
Georgi Gerganov
|
5fbfe384d4
server : improve error reporting (#13680)
|
пре 8 месеци |
 Robin Davidsson
|
0d5c742161
server : Add the endpoints /api/tags and /api/chat (#13659)
|
пре 8 месеци |
 Dorin-Andrei Geman
|
42158ae2e8
server : fix first message identification (#13634)
|
пре 8 месеци |
|
Georgi Gerganov
|
797f2ac062
kv-cache : simplify the interface (#13660)
|
пре 8 месеци |
|
Georgi Gerganov
|
e298d2fbd0
kv-cache : add SWA support (#13194)
|
пре 8 месеци |
 Isaac McFadyen
|
6a2bc8bfb7
server : added --no-prefill-assistant flag (#13608)
|
пре 8 месеци |
|
Xuan-Son Nguyen
|
6aa892ec2a
server : do not return error out of context (with ctx shift disabled) (#13577)
|
пре 8 месеци |
 Olivier Chafik
|
3198405e98
`common`: add partial regex support (#12808)
|
пре 8 месеци |
|
Georgi Gerganov
|
053174436f
server : passthrough the /models endpoint during loading (#13535)
|
пре 8 месеци |
|
Xuan-Son Nguyen
|
360a9c98e1
server : fix cache_tokens bug with no cache_prompt (#13533)
|
пре 8 месеци |
 Anthony Umfer
|
9a390c4829
tools : fix uninitialized llama_batch in server (#13436)
|
пре 8 месеци |
|
Xuan-Son Nguyen
|
33eff40240
server : vision support via libmtmd (#12898)
|
пре 8 месеци |
|
Georgi Gerganov
|
6562e5a4d6
context : allow cache-less context for embeddings (#13108)
|
пре 8 месеци |
 oobabooga
|
233461f812
sampling : Integrate Top-nσ into main sampling chain (and add it to the server) (#13264)
|
пре 8 месеци |
 Diego Devesa
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
пре 8 месеци |
