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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: ValueError: current platform cpu does not support ray.
- [Bug]: Qwen3 tool call
- [RFC]: Integrate MPK (Mirage) compiler as an experimental execution backend to vLLM
- [Feature]: Add support for Apple MPS(Metal Performance Shaders)
- [RFC]: Disaggregated Everything - Token In <> Token Out API Server
- [Bug]: RuntimeError bug with GLM-4.5V-FP8 on A800
- [Bugfix] Fix dual-stack binding when --host is empty
- [Bug]: Can't run Qwen3-235B-A22B-Thinking-2507-FP4 NVFP4 model
- Split compressed_tensors_moe.py into separate wna16, int8, fp8, nvfp4
- [TPU] Add numba dependency to tpu requirements.
- Docs
- Python not yet supported