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 supported21 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: Support multi-modal inputs for OpenAI Response API
- [RFC]: Unified Parser for reasoning, tool calling
- fix: Resolve kv_cache_dtype='auto' to actual dtype and log it (#32843)
- [Feature][Tool Parser] Add dedicated parser for Qwen2.5-Coder models
- [Feature] support mtp3
- [Frontend] add previous context to whisper transcription over 30s audio
- [Bug]: Hitting close to 100% cache causes spike in waiting and kills throughput
- [Docs] Fix install device tabs being out of sync when directly linked to
- [Bug]: v0.10.2 Qwen 3 Next 80b FP8 Slow first request and potential format mismatch: seq_len (4) < num_heads (8)
- [RFC]: Support Prefill Context Parallel (PCP)
- Docs
- Python not yet supported