 Diego Devesa
|
f75b830647
chat : include kwargs in template example (#15309)
|
hace 5 meses |
 Georgi Gerganov
|
d32e03f449
server : add SWA checkpoints (#15293)
|
hace 5 meses |
 Sigbjørn Skjæret
|
b3e16665e1
server : enable -td and -tbd parameters (#15172)
|
hace 5 meses |
 Copilot
|
d8914fc47e
common : add --override-tensor-draft, --cpu-moe-draft and --n-cpu-moe-draft parameters (#15191)
|
hace 5 meses |
 Xuan-Son Nguyen
|
53d0a12658
server : allow specifying reasoning_format in HTTP request (#15238)
|
hace 5 meses |
 Johannes Gäßler
|
f906275537
server: enable token array inputs for OAI API (#15001)
|
hace 5 meses |
 g2mt
|
94933c8c2e
server : implement universal assisted decoding (#12635)
|
hace 5 meses |
 Lukas Straub
|
a9f77a8be3
server : add openai-style logit_bias support (#14946)
|
hace 5 meses |
 Daniel Bevenius
|
41e78c567e
server : add support for `embd_normalize` parameter (#14964)
|
hace 5 meses |
 Molly Sophia
|
adef81781a
server : allow setting `--reverse-prompt` arg (#14799)
|
hace 5 meses |
 IsaacDynamo
|
b4efd77f8a
server : add parse_special option to /tokenize endpoint (#14783)
|
hace 6 meses |
|
Georgi Gerganov
|
6ffd4e9c44
server : pre-calculate EOG logit biases (#14721)
|
hace 6 meses |
|
Georgi Gerganov
|
538cc77f7f
server : fix handling of the ignore_eos flag (#14710)
|
hace 6 meses |
 Douglas Hanley
|
0c1df14b5f
server : fix pooled embedding output (#14645)
|
hace 6 meses |
 Alawode Oluwandabira
|
17a1f0d2d4
server: Add ability to mount server at prefix (#14544)
|
hace 6 meses |
 matteo
|
caf5681fcb
server : support jinja extra template kwargs (Qwen3 enable_thinking feature), from command line and from client (#13196)
|
hace 6 meses |
|
Georgi Gerganov
|
7b50d589a8
kv-cells : fix tracking of seq_pos (#14339)
|
hace 6 meses |
|
Georgi Gerganov
|
4c9fdfbe15
ubatch : new splitting logic (#14217)
|
hace 7 meses |
 aa956
|
d67341dc18
server : add server parameters for draft model cache type (#13782)
|
hace 7 meses |
|
Georgi Gerganov
|
89fea80d29
server : fix incorrect usage of llama_get_embeddings() (#14225)
|
hace 7 meses |
|
Georgi Gerganov
|
d3e64b9f49
llama : rework embeddings logic (#14208)
|
hace 7 meses |
 Eric Curtin
|
cd355eda7d
server : When listening on a unix domain socket don't print http:// and port (#14180)
|
hace 7 meses |
|
Georgi Gerganov
|
ffad043973
server : fix SWA condition for full context reprocess (#14163)
|
hace 7 meses |
|
Georgi Gerganov
|
7d516443dd
server : re-enable SWA speculative decoding (#14131)
|
hace 7 meses |
 Taylor
|
2baf07727f
server : pass default --keep argument (#14120)
|
hace 7 meses |
 Juk Armstrong
|
3a12db23b6
Fixed spec timings to: accepted/tested instead of accepted/drafted (#14104)
|
hace 7 meses |
|
Georgi Gerganov
|
87d34b381d
server : fix LRU check (#14079)
|
hace 7 meses |
|
Georgi Gerganov
|
745aa5319b
llama : deprecate llama_kv_self_ API (#14030)
|
hace 7 meses |
|
Georgi Gerganov
|
3637576288
server : disable speculative decoding for SWA models (#13970)
|
hace 7 meses |
 Olivier Chafik
|
c9bbc77931
`server`: update deepseek reasoning format (pass reasoning_content as diffs) (#13933)
|
hace 7 meses |
