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
- [Usage]: how to make one quantized model(w4a FP8). I used llm-compressor make one. But it not work in vllm 0.10.2.
- [RFC]: Limit the use of envvars in vLLM
- [Bug]: vLLM server not starting when running Qwen/Qwen3-VL-30B-A3B-Instruct on 2 A6000 GPUs.
- [CI/Build] Add aime25 eval to gpt-oss CI
- [Bugfix] Handle escaped characters in GLM tool parser to prevent double serialization
- Fix/responses api harmony channel metadata #28262
- [Kernel] Unified attention kernel performance tuning
- [Core] Extending I/O Plugins
- [Bug]: kimi-k2-thinking on AMD MI300X not working
- [DO NOT LAND] Prototype Helion kernel in vLLM
- Docs
- Python not yet supported