vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported2 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Usage]: How can i user scheduler with OpenAI Compatible Server
- [New Model]: Reflection-Llama-3.1-70B
- [Bug]: num_scheduler_steps > 1, n > 1 raise error
- [New Model]: Support for Idefics3 8B Llama3
- [Bug]: how to set gpu id in code?
- [Bug]: AssertionError when using automatic prefix caching and prompt_logprobs
- [Performance]: Using vLLM for Llama3.1 405b fp8 on 8xH100 yields poor throughput
- [Kernel] Build flash-attn from source
- [BugFix] Propagate 'trust_remote_code' setting in internvl and minicpmv
- [Frontend][Core] Move guided decoding params into sampling params
- Docs
- Python not yet supported