 Behnam M
|
cd108e641d
server : add a `/health` endpoint (#4860)
|
%!s(int64=2) %!d(string=hai) anos |
 Georgi Gerganov
|
67984921a7
server : fix n_predict check (#4798)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
012cf349ae
server : send token probs for "stream == false" (#4714)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
32866c5edd
editorconfig : fix whitespace and indentation #4710
|
%!s(int64=2) %!d(string=hai) anos |
 minarchist
|
5d7002d437
server : add --override-kv parameter (#4710)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
9fbda719de
clip : refactor + bug fixes (#4696)
|
%!s(int64=2) %!d(string=hai) anos |
 Justine Tunney
|
db49ff8ed7
server : replace sleep with condition variables (#4673)
|
%!s(int64=2) %!d(string=hai) anos |
 SakuraUmi
|
60f55e888c
server : fix OpenAI server sampling w.r.t. penalty. (#4675)
|
%!s(int64=2) %!d(string=hai) anos |
 Karthik Sethuraman
|
b93edd22f5
server : allow to generate multimodal embeddings (#4681)
|
%!s(int64=2) %!d(string=hai) anos |
|
Justine Tunney
|
65e5f6dadb
Fix OpenAI server sampling w.r.t. temp and seed (#4668)
|
%!s(int64=2) %!d(string=hai) anos |
 Alexey Parfenov
|
6123979952
server : allow to specify custom prompt for penalty calculation (#3727)
|
%!s(int64=2) %!d(string=hai) anos |
 olexiyb
|
0ffc92d2d2
server : disable llm logs if SERVER_VERBOSE is off (#3792)
|
%!s(int64=2) %!d(string=hai) anos |
 AdithyanI
|
8edd2b40fd
server : fix grammar being ignored (#4494)
|
%!s(int64=2) %!d(string=hai) anos |
|
Alexey Parfenov
|
eb16dae7e7
server : fix possible ambiguity in content type charset (#4501)
|
%!s(int64=2) %!d(string=hai) anos |
 mzcu
|
62bd52b7bf
server : allow requests larger than 8K (#4500)
|
%!s(int64=2) %!d(string=hai) anos |
 ShadovvBeast
|
88ae8952b6
server : add optional API Key Authentication example (#4441)
|
%!s(int64=2) %!d(string=hai) anos |
 shibe2
|
948ff137ec
server : fix handling of characters that span multiple tokens when streaming (#4446)
|
%!s(int64=2) %!d(string=hai) anos |
 Vladimir Zorin
|
d9d4cfef64
server : fix local model name in server (#4420)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
bcc0eb4591
llama : per-layer KV cache + quantum K cache (#4309)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
05cd6e5036
server : recognize cache_prompt parameter in OAI API (#4347)
|
%!s(int64=2) %!d(string=hai) anos |
 Ed Lee
|
33e171d1e9
server : fix OpenAI API `stop` field to be optional (#4299)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
d5a1cbde60
llama : support optional tensors (#4283)
|
%!s(int64=2) %!d(string=hai) anos |
 Ziad Ben Hadj-Alouane
|
1d144112c0
server : add --log-disable to disable logging to file (#4260)
|
%!s(int64=2) %!d(string=hai) anos |
|
Ziad Ben Hadj-Alouane
|
f43f09366d
server : add single-client multi-prompt support (#4232)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
af19d35734
server : OAI API compatibility (#4198)
|
%!s(int64=2) %!d(string=hai) anos |
 Haohui Mai
|
55978ce09b
Fix incorrect format strings and uninitialized variables. (#4133)
|
%!s(int64=2) %!d(string=hai) anos |
 SoftwareRenderer
|
936c79b227
server : relay error messages (#4131)
|
%!s(int64=2) %!d(string=hai) anos |
 Kerfuffle
|
91f6499393
Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040)
|
%!s(int64=2) %!d(string=hai) anos |
|
Alexey Parfenov
|
d96ca7ded7
server : fix crash when prompt exceeds context size (#3996)
|
%!s(int64=2) %!d(string=hai) anos |
 Mihai
|
57ad015dc3
server : add min_p param (#3877)
|
%!s(int64=2) %!d(string=hai) anos |
