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 supported15 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: RuntimeError: NCCL error: unhandled cuda error
- [Quant] Refactor CompressedTensorsConfig
- [RFC]: ATTN-FFN Disaggregation for MoE Models
- [Refactor] Small cleanup for quantized FusedMoE
- [gpt-oss]Fix gpt-oss model streaming output with spec decoding
- [Bug]: Hangs on mulit-node setup when len(prompt) > max_model_len
- [RFC]: Responses API full functionality without stores
- [Feature]: More Frequently Updated Docker Images
- [Model] Support LLAVA ONEVISION 1.5
- [P/D] [NixlConnector] Draft: zmq handshake abstraction
- Docs
- Python not yet supported