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 supported14 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [CI Failure]:
- Fix 500 /tokenize errors and 400 v1/chat/completions errors when using truncate_prompt_tokens and sending /tokenize and v1/chat/completions requests under high concurrency
- [AMD] Amd/deepseek aiter fusions
- [LoRA] Support Quantized Adapters
- adding constraint updates of cos-sin to improve mrope performance
- fix(gguf): Use EOS token ID from GGUF metadata instead of HF tokenizer
- Don't compile vision encoder for Transformers backend
- [Frontend] Implement `service_tier` for OpenAI API endpoints
- MLA Based Eagle3
- [Bug]: vllm 12.0 run 120b tp=8 in blackwell 5060ti*7+5090 with hit nccl error in cuda graph
- Docs
- Python not yet supported