 Alexey Parfenov
|
684780141a
server : allow to specify tokens as strings in logit_bias (#5003)
|
il y a 1 an |
 Xuan Son Nguyen
|
907e08c110
server : add llama2 chat template (#5425)
|
il y a 1 an |
 Riley Stewart
|
7c777fcd5d
server : fix prompt caching for repeated prompts (#5420)
|
il y a 1 an |
 Justin Parker
|
f3e2b4fa3f
server : update `/props` with "total_slots" value (#5373)
|
il y a 1 an |
|
Alexey Parfenov
|
213d1439fa
server : remove model.json endpoint (#5371)
|
il y a 1 an |
|
Justin Parker
|
8a79c591de
server : include total "num_slots" in props endpoint (#5349)
|
il y a 1 an |
 Michael Coppola
|
31e7903221
server : add `dynatemp_range` and `dynatemp_exponent` (#5352)
|
il y a 1 an |
 Niall Coates
|
4ffc7a17d4
server : various fixes for the prompt field in /completion (#5300)
|
il y a 1 an |
|
Alexey Parfenov
|
a2d60c9158
server : allow to get default generation settings for completion (#5307)
|
il y a 1 an |
 Michael Klimenko
|
52bb63c708
refactor : switch to emplace_back to avoid extra object (#5291)
|
il y a 1 an |
 Georgi Gerganov
|
5cb04dbc16
llama : remove LLAMA_MAX_DEVICES and LLAMA_SUPPORTS_GPU_OFFLOAD (#5240)
|
il y a 1 an |
|
Georgi Gerganov
|
e6f291d158
server : fix context shift (#5195)
|
il y a 1 an |
 Wu Jian Ping
|
c82d18e863
server : embeddings compatibility for OpenAI (#5190)
|
il y a 1 an |
 Abhilash Majumder
|
0f648573dd
ggml : add unified SYCL backend for Intel GPUs (#2690)
|
il y a 2 ans |
|
Michael Klimenko
|
35a2ee9143
Remove unused data and add fixes (#5154)
|
il y a 2 ans |
 Maximilian Winter
|
ec903c0341
server : add self-extend support (#5104)
|
il y a 2 ans |
|
Xuan Son Nguyen
|
48c857aa10
server : refactored the task processing logic (#5065)
|
il y a 2 ans |
|
Xuan Son Nguyen
|
821f0a271e
server : defer tasks when "slot unavailable" (#5018)
|
il y a 2 ans |
|
Georgi Gerganov
|
0ea069b87b
server : fix prompt caching with system prompt (#4914)
|
il y a 2 ans |
 Ziad Ben Hadj-Alouane
|
356327feb3
server : fix deadlock that occurs in multi-prompt scenarios (#4905)
|
il y a 2 ans |
 makomk
|
ee8243adaa
server : fix crash with multimodal models without BOS token (#4904)
|
il y a 2 ans |
 slaren
|
e7e4df031b
llama : ggml-backend integration (#4766)
|
il y a 2 ans |
|
Georgi Gerganov
|
1d118386fe
server : fix infill when prompt is empty (#4833)
|
il y a 2 ans |
 Laura
|
4330bd83fe
server : implement credentialed CORS (#4514)
|
il y a 2 ans |
|
Michael Coppola
|
27379455c3
server : support for multiple api keys (#4864)
|
il y a 2 ans |
 Behnam M
|
eab6795006
server : add `LOG_INFO` when model is successfully loaded (#4881)
|
il y a 2 ans |
 Isaac McFadyen
|
2f043328e3
server : fix typo in model name (#4876)
|
il y a 2 ans |
|
Georgi Gerganov
|
5c1980d8d4
server : fix build + rename enums (#4870)
|
il y a 2 ans |
|
Behnam M
|
cd108e641d
server : add a `/health` endpoint (#4860)
|
il y a 2 ans |
|
Georgi Gerganov
|
67984921a7
server : fix n_predict check (#4798)
|
il y a 2 ans |
