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
- [Bug]: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.1%, Prefix cache hit rate: 11.9%
- [Bug]: vllm 0.10.1+gptoss wheel breaks on glibc 2.28
- [feat] preserve metadata for quantized model weight reload
- [NVFP4] Enable MOE support for SM_120 (RTX 5090)
- [Performance]: Compiled `QuantFP8.forward_native` group quantization (1, 128) slower than CUDA on H100/RTX5090
- CLI: Ignore SIGTSTP signal (Ctrl-Z)
- fix json schema alias serializing when streaming
- [Performance]: RTX 6000 PRO - FP8 in sglang is faster
- [RFC]: Enable libtorch-ABI-stable vLLM cuda wheels
- [Installation]: Unable to Install vllm with python 3.14
- Docs
- Python not yet supported