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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Model Runner V2] Reuse constant tensors in input prep
- [ROCm][Quantization] Simplify activation scale passing for triton mxfp4 w4afp8
- [Usage]: vllm 可以部署grounding-dino模型吗
- [Bug]: [MooncakeConnector] Decode side requests stuck in WAITING_FOR_REMOTE_KVS indefinitely on transfer failure, causing HBM leak
- [Bug]: jetson agx thor报错
- [Bugfix] Narrow kv_cache mempool context to prevent sleep mode regressions
- [Bugfix] Fix suffix decoding crash from negative num_new_tokens
- [Bugfix] Fix MXFP4A16 degenerate output via compressed-tensors bump
- [Bug]: Why does deploying Qwen3-32B-AWQ via vllm:v0.10.1.1 result in different outputs for the same input?
- fix qwen3 streaming reasoning parser when thinking is disabled
- Docs
- Python not yet supported