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
- [Model] Add support for Nemotron-Flash-3B
- [RFC]: Path to vLLM 1.0 Release
- [Bug]: 5090 cannot run Qwen3-30B-A3B-NVFP4!
- [Async Scheduling] Support async scheduling with ray backend
- [Feat][Sched] Add SJF Scheduling Policy
- [Performance]: DeepSeek-v3.2 throughput&TTFT&TPOT is much slower than DeepSeek-v3.1 on 8*H200
- [V1][Spec Decode] Add Dynamic SD
- [Draft] AFD implementation for step3
- [Kernels] Add support for hybrid DeepEP
- [feat] Implement Elastic Speculation: Adaptive Draft Length + Confidence-Based Early Exit
- Docs
- Python not yet supported