codelion optillm issues

codelion / optillm

Optimizing inference proxy for LLMs

Apache License 2.0

1.6k stars 128 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Warning: Do not support sampling multiple responses

#99 Mushoz opened 5 days ago
4
Add aime eval script

#98 codelion closed 6 days ago
0
Add a web search plugin that can be used to ground the responses

#97 codelion opened 6 days ago
0
How to reproduce RTC Eval 100% locally?

#96 botelhorui opened 1 week ago
1
Fix entropy decoding in local server

#95 codelion closed 1 week ago
0
Update optillm.py

#94 codelion closed 1 week ago
0
I want to try to use this project for local llm, but I'm not sure how.

#93 matbee-eth opened 1 week ago
1
add dependency and bump version

#92 codelion closed 1 week ago
0
fix dependencies

#91 codelion closed 1 week ago
0
Feat add local inference

#89 codelion closed 1 week ago
0
fix msg

#88 femto closed 2 weeks ago
0
Feat update router training

#87 codelion closed 2 weeks ago
0
Update init file to expose methods

#86 codelion closed 2 weeks ago
0
docs: update README.md

#85 eltociear closed 2 weeks ago
0
parse conversation reports error

#84 femto closed 2 weeks ago
0
deepseek can't support n > 1

#83 femto opened 2 weeks ago
2
Fix litellm wrapper for claude

#81 codelion closed 3 weeks ago
0
Some modification to clear the code

#80 shamanez closed 4 weeks ago
0
Add plugins

#79 codelion closed 4 weeks ago
0
Fix init py

#78 codelion closed 4 weeks ago
0
Update setup.py

#77 codelion closed 4 weeks ago
0
Update README.md

#76 codelion closed 4 weeks ago
0
Fix setup.py entrypoint

#75 codelion closed 4 weeks ago
0
Update README.md

#74 codelion closed 4 weeks ago
0
Feature: easy to add new approaches

#72 ErykCh closed 2 weeks ago
1
Resulting docker image size (6.36GB) is quite large - is there any opportunity to reduce this?

#71 sammcj closed 3 weeks ago
3
Thanks for adding the entropy based sampling, by any chance do you have a comprasion with other alternative methods?

#70 shamanez closed 1 month ago
2
Setting the default approach doesn't work

#69 ErykCh closed 2 weeks ago
6
Ambiguous configuration for mcts

#68 ErykCh closed 2 weeks ago
6
I get the following error: list index out of range

#67 ErykCh opened 1 month ago
14
Implement cot decoding with llama.cpp

#65 codelion closed 1 week ago
5
Request for Reference Citations for CoT Prompting Methods

#64 qsunyuan closed 1 month ago
1
Scripts to reproduce benchmark results

#63 zhxieml closed 1 month ago
1
Feat router

#62 codelion closed 1 month ago
0
Using llama-server issue with 'no_key' API key

#61 s-hironobu closed 1 month ago
1
(MOA) Fails with "List Index Out of Range" Error on OpenAI-Compatible Ollama API Endpoint

#60 chrisoutwright closed 1 month ago
6
I can see cot_decode method has implemented, but we can't use it with the proxy.

#59 shamanez closed 1 month ago
13
When I tried the optillm with my own openai API compatible hosted model I get this error

#58 shamanez closed 1 month ago
6
Is there any possibility we align some interest?

#57 femto closed 1 month ago
1
Add a lighting template for running optillm

#56 codelion opened 1 month ago
1
synced

#55 vanetreg closed 1 month ago
0
Integration with Gemini 1.5 models

#54 tranhoangnguyen03 closed 1 month ago
2
token counting

#52 darkacorn closed 1 month ago
2
[Question]: Which paper is mcts.py based on?

#51 RomanKoshkin closed 1 month ago
1
Merge branch 'main' of https://github.com/codelion/optillm

#50 vanetreg closed 1 month ago
0
Feat add plugin for privacy

#49 codelion closed 1 month ago
0
Add cli log flag

#48 jovanwongzixi closed 1 month ago
1
Add push to hub

#47 lewtun closed 1 month ago
0
Fix confidence calculation

#46 jovanwongzixi closed 1 month ago
0
Possible error in calculate_confidence() logic for cot_decoding.py

#45 jovanwongzixi closed 1 month ago
1