 Georgi Gerganov
|
644fd71b44
sampling : refactor + optimize penalties sampler (#10803)
|
пре 1 година |
 Xuan Son Nguyen
|
adffa6ffd5
common : improve -ctv -ctk CLI arguments (#10806)
|
пре 1 година |
 CentricStorm
|
5555c0c1f6
docs: update server streaming mode documentation (#9519)
|
пре 1 година |
|
CentricStorm
|
4b4d92b098
docs: fix server documentation formatting (#10776)
|
пре 1 година |
 Yüg
|
a86ad841f1
server : add flag to disable the web-ui (#10762) (#10751)
|
пре 1 година |
|
Xuan Son Nguyen
|
3573fa8e7b
server : (refactor) no more json in server_task input (#10691)
|
пре 1 година |
|
Georgi Gerganov
|
ce4a7b8493
server : various fixes (#10704)
|
пре 1 година |
|
Xuan Son Nguyen
|
6c5bc0625f
server : (refactoring) do not rely on JSON internally (#10643)
|
пре 1 година |
|
Xuan Son Nguyen
|
91c36c269b
server : (web ui) Various improvements, now use vite as bundler (#10599)
|
пре 1 година |
 Nikolaos Pothitos
|
82bca2257b
readme : add option, update default value, fix formatting (#10271)
|
пре 1 година |
|
Xuan Son Nguyen
|
642330ac7c
llama : add enum for built-in chat templates (#10623)
|
пре 1 година |
|
Georgi Gerganov
|
8648c52101
make : deprecate (#10514)
|
пре 1 година |
 haopeng
|
64ed2091b2
server: Add "tokens per second" information in the backend (#10548)
|
пре 1 година |
|
Georgi Gerganov
|
47f931c8f9
server : enable cache_prompt by default (#10501)
|
пре 1 година |
 Johannes Gäßler
|
4e54be0ec6
llama/ex: remove --logdir argument (#10339)
|
пре 1 година |
 Alexey Parfenov
|
ff7fb670d0
server : add missing docs (#10269)
|
пре 1 година |
|
Georgi Gerganov
|
b141e5f6ef
server : enable KV cache defrag by default (#10233)
|
пре 1 година |
|
Xuan Son Nguyen
|
a71d81cf8c
server : revamp chat UI with vuejs and daisyui (#10175)
|
пре 1 година |
|
Xuan Son Nguyen
|
9e0ecfb697
server : clarify /slots endpoint, add is_processing (#10162)
|
пре 1 година |
|
Georgi Gerganov
|
8d8ff71536
llama : remove Tail-Free sampling (#10071)
|
пре 1 година |
 wwoodsTM
|
ff252ea48e
llama : add DRY sampler (#9702)
|
пре 1 година |
|
Xuan Son Nguyen
|
958367bf53
server : refactor slot input data, move tokenizer to HTTP thread (#10023)
|
пре 1 година |
|
Georgi Gerganov
|
8901755ba3
server : add n_indent parameter for line indentation requirement (#9929)
|
пре 1 година |
|
Georgi Gerganov
|
223c25a72f
server : improve infill context reuse (#9894)
|
пре 1 година |
|
Georgi Gerganov
|
d4c19c0f5c
server : accept extra_context for the infill endpoint (#9874)
|
пре 1 година |
|
Georgi Gerganov
|
c7181bd294
server : reuse cached context chunks (#9866)
|
пре 1 година |
|
Georgi Gerganov
|
edc265661c
server : add option to time limit the generation phase (#9865)
|
пре 1 година |
|
Georgi Gerganov
|
1bde94dd02
server : remove self-extend features (#9860)
|
пре 1 година |
|
Georgi Gerganov
|
95c76e8e92
server : remove legacy system_prompt feature (#9857)
|
пре 1 година |
|
Georgi Gerganov
|
11ac9800af
llama : improve infill support and special token detection (#9798)
|
пре 1 година |
