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
- Test mi300 2
- PD disagg: skip decode-side re-tokenization in PD serving with vllm-router + NixlConnector
- [Bug]: CUDA OOM with Kimi-K2.5 NVFP4 on both TP4 and TP8
- [BugFix] Prevent orphaned process on NCCL destroy
- Add HAProxy to a list of load balancers in documentation
- [Model] Add MTP support for JoyAI-LLM Flash
- [PD] Bump Nixl version
- [KV Cache][TurboQuant] Add official 3-bit and 4-bit grouped TurboQuant modes
- [Feature] Add Int8/FP8-quantized all-reduce
- [Quantization][Autoround][Toolkit] Add W4A16 Support
- Docs
- Python not yet supported