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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Tool Parser] Return early for unlisted tool names in InternLM2 parser
- [Bug]: vLLM embedding hang with Qwen3-Embedding when chunked prefill is enabled
- [Bug]: Streaming Parser Engine leaks JSON structure into `arguments` for JSON-envelope tool-call configs without an `arg_converter`
- [Bugfix] MiniMax-M3 tool parser: stream tool-call arguments incrementally
- [Bugfix][Parser] Use DeepSeek tool slot name for wrapper unwrapping
- [Bugfix][Parser] Stream JSON envelope argument values
- [Bugfix][Tokenizer] Reject invalid DeepSeek history tool arguments
- [Doc] Use validated relative links for code references in design docs
- [Bugfix] Size numpy arrays by nbytes in multimodal cache accounting
- feat: Add AMD NPU vision support for Qwen2.5-VL
- Docs
- Python not yet supported