 Georgi Gerganov
|
b7f9010d24
server : disable checkpoints with mtmd (#17045)
|
hace 2 meses |
|
Georgi Gerganov
|
13b339bcd9
server : do not default to multiple slots with speculative decoding (#17017)
|
hace 2 meses |
|
Georgi Gerganov
|
66d8eccd42
server : do context shift only while generating (#17000)
|
hace 2 meses |
|
Georgi Gerganov
|
48bd26501b
server : add props.model_alias (#16943)
|
hace 2 meses |
 Xuan-Son Nguyen
|
070ff4d535
mtmd: add --image-min/max-tokens (#16921)
|
hace 2 meses |
|
Georgi Gerganov
|
2f966b8ed8
clip : use FA (#16837)
|
hace 2 meses |
|
Georgi Gerganov
|
cd5e3b5754
server : support unified cache across slots (#16736)
|
hace 2 meses |
|
Georgi Gerganov
|
c22473b580
server : don't print user inputs to console (#16871)
|
hace 2 meses |
 Daniel Bevenius
|
0f715b4e75
server : fix typos in server.cpp comments [no ci] (#16883)
|
hace 2 meses |
|
Georgi Gerganov
|
b52edd2558
server : remove n_past (#16818)
|
hace 2 meses |
|
Georgi Gerganov
|
85a7d8677b
memory : remove KV cache size padding (#16812)
|
hace 2 meses |
 Johannes Gäßler
|
0bf47a1dbb
server: add memory breakdown print (#16740)
|
hace 2 meses |
 matteo
|
8cf6b42d46
server : send partial stop string when <EOG> is reached (#15007)
|
hace 2 meses |
|
Georgi Gerganov
|
17304cbcc1
server : fix img token logs (#16595)
|
hace 3 meses |
|
Georgi Gerganov
|
554fd578a5
server : fix mtmd checkpoints (#16591)
|
hace 3 meses |
|
Georgi Gerganov
|
bc07349a7f
server : dynamic token limit for prompt cache (#16560)
|
hace 3 meses |
 Yann Follet
|
31d0ff1869
server / ranking : add sorting and management of top_n (#16403)
|
hace 3 meses |
|
Georgi Gerganov
|
e60f01d941
server : fix division by zero when reporting stats (#16501)
|
hace 3 meses |
 Radoslav Gerganov
|
68ee98ae18
server : return HTTP 400 if prompt exceeds context length (#16486)
|
hace 3 meses |
|
Radoslav Gerganov
|
cdb6da468c
server : log requests to /v1/completions (#16495)
|
hace 3 meses |
|
Georgi Gerganov
|
d00cbea63c
server : host-memory prompt caching (#16391)
|
hace 3 meses |
 issixx
|
d2ee056e1d
server : fix cancel pending task (#16467)
|
hace 3 meses |
|
Georgi Gerganov
|
7fdd16b432
server : improve context checkpoint logic (#16440)
|
hace 3 meses |
|
Georgi Gerganov
|
df1b612e29
server : add `/v1/health` endpoint (#16461)
|
hace 3 meses |
 ddh0
|
f6dcda3900
server : context checkpointing for hybrid and recurrent models (#16382)
|
hace 3 meses |
 Isaac McFadyen
|
e0539eb6ae
webui: switch to hash-based routing (alternative of #16079) (#16157)
|
hace 3 meses |
 Douglas Hanley
|
b5bd037832
llama : add support for qwen3 reranker (#15824)
|
hace 3 meses |
 Benni
|
459c0c2c1a
server: fix SSE and OpenAI compatibility for error messages when streaming (#16109)
|
hace 4 meses |
|
Radoslav Gerganov
|
2b6b55a59f
server : include usage statistics only when user request them (#16052)
|
hace 4 meses |
 Aleksander Grygier
|
a7a98e0fff
SvelteKit-based WebUI (#14839)
|
hace 4 meses |
