 Daniel Bevenius
|
16639ba217
common : use two decimal places for float arg help messages (#19048)
|
пре 1 недеља |
 Xuan-Son Nguyen
|
51fa458a92
server : support preserving reasoning_content in assistant message (#18994)
|
пре 1 недеља |
 손희준
|
fbbf3ad190
server: /v1/responses (partial) (#18486)
|
пре 1 недеља |
 ddh0
|
13f1e4a9ca
llama : add adaptive-p sampler (#17927)
|
пре 2 недеља |
|
Xuan-Son Nguyen
|
ce3bf9b1a4
server: update docs for sleeping [no ci] (#18777)
|
пре 3 недеља |
|
Xuan-Son Nguyen
|
f5acfb2ffa
server: (router) add stop-timeout option (#18350)
|
пре 1 месец |
|
Xuan-Son Nguyen
|
179fd82a72
gen-docs: automatically update markdown file (#18294)
|
пре 1 месец |
|
Xuan-Son Nguyen
|
86af848153
server: (docs) remove mention about extra_args (#18262)
|
пре 1 месец |
|
Xuan-Son Nguyen
|
ddcb75dd8a
server: add auto-sleep after N seconds of idle (#18228)
|
пре 1 месец |
|
Xuan-Son Nguyen
|
9e39a1e6a9
server: support load model on startup, support preset-only options (#18206)
|
пре 1 месец |
 Pascal
|
14931a826e
arg: fix order to use short form before long form (#18196)
|
пре 1 месец |
|
Xuan-Son Nguyen
|
98c1c7a7bf
presets: refactor, allow cascade presets from different sources, add global section (#18169)
|
пре 1 месец |
|
Pascal
|
6ce3d85796
server: (webui) add --webui-config (#18028)
|
пре 1 месец |
|
Xuan-Son Nguyen
|
7b1db3d3b7
arg: clarify auto kvu/np being set on server (#17997)
|
пре 1 месец |
 2114L3
|
5f5f9b4637
server: Update README.md incorrect argument (#18073)
|
пре 1 месец |
|
Xuan-Son Nguyen
|
380b4c984e
common: support negated args (#17919)
|
пре 1 месец |
|
Xuan-Son Nguyen
|
54a0fee4b7
arg: add -mm and -mmu as short form of --mmproj and --mmproj-url (#17958)
|
пре 1 месец |
|
Pascal
|
f32ca51bfe
server: add presets (config) when using multiple models (#17859)
|
пре 1 месец |
|
Xuan-Son Nguyen
|
37a4f63244
server : add development documentation (#17760)
|
пре 1 месец |
 Georgi Gerganov
|
2bc96931d2
server : make cache_reuse configurable per request (#17858)
|
пре 1 месец |
|
Xuan-Son Nguyen
|
c42712b056
server: support multiple generations from one prompt (OAI "n" option) (#17775)
|
пре 1 месец |
|
Xuan-Son Nguyen
|
ec18edfcba
server: introduce API for serving / loading / unloading multiple models (#17470)
|
пре 2 месеци |
|
Xuan-Son Nguyen
|
7733409734
common: improve verbosity level definitions (#17630)
|
пре 2 месеци |
 Fredrik Hultin
|
ddf9f94389
server : add Anthropic Messages API support (#17570)
|
пре 2 месеци |
|
Xuan-Son Nguyen
|
e509411cf1
server: enable jinja by default, update docs (#17524)
|
пре 2 месеци |
 Aidan
|
eeee367de5
server: fix correct time_ms calculation in prompt_progress (#17093)
|
пре 2 месеци |
|
손희준
|
fd2f84f468
docs: Clarify the endpoint that webui uses (#17001)
|
пре 2 месеци |
|
Georgi Gerganov
|
b52edd2558
server : remove n_past (#16818)
|
пре 3 месеци |
|
Pascal
|
12bbc3fa50
refactor: centralize CoT parsing in backend for streaming mode (#16394)
|
пре 3 месеци |
|
Georgi Gerganov
|
df1b612e29
server : add `/v1/health` endpoint (#16461)
|
пре 3 месеци |
