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 supported24 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [BugFix] Dense + multinode + DP > 1 port conflicts
- [Attention] Validate DIFFKV via backend selection
- [SpecDecode] Reduce TP communication for large-vocab draft models in DFlash/PARD speculative decoding
- fix: skip string delimiters in Gemma4 nested array bracket-depth tracking
- fix: Disable VLLM_ROCM_USE_AITER_FP4BMM by default to prevent crashes on MI300X
- [Core]Fix/handle kernel failures
- [WIP] Enable `torch.cond` for dynamic block-scaled MM kernels
- [Model] Gemma4: robust quantized MoE expert weight loading
- [Usage]: qwen3-asr-1.7b pre-allocated encoder cache size limit
- [V1] Async parallel startup for EngineCore processes in DP/TP scenarios
- Docs
- Python not yet supported