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 supported4 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Usage]: Inference metrics printing problem
- [Bug]: vllm0.6.2 Using FLASHINFER to start VLLM reported an error, enabling -- quantification gptq -- kv cache dtype fp8_e5m2
- [Installation]: build error from source on 4090
- [Usage]: VLLM 0.6.2 includes vllm-flash-attn, is it no longer necessary to install flash-attn separately?
- [Bug]: Simultaneous mm calls lead to permanently degraded performance.
- Compile
- [Bug]: new beam search implementation ignores stop conditions
- [Bug]: Streaming response fails after one token (0.5.3.post1)
- [Bug]: AsyncLLMEngine stuck on a single too long request
- [Feature]: Improve Logging For Embedding Models
- Docs
- Python not yet supported