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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [compile] Skip computation_graph.py dump unless debug/trace is active
- [Feature] [NVFP4]: Unfused global scales for microscale quantization
- Fix LFM2 decoding on ROCm
- [MoE Refactor] Add EplbManager class to handle EPLB functionality
- Parallel Compilation Protection Downgrade
- [Bugfix] avoid loading errors for dense qwen3_next models
- [Platform] Allow BackendEnum dynamic register
- [ROCm][Bug]: Quark MXFP4 `w_mxfp4_a_mxfp4` linear path corrupts Qwen1.5-MoE output on MI355
- [ROCm] Add AITER fused dual RMSNorm for MLA
- [Bugfix] Raise clear error when --enable-eplb on non-EPLB model
- Docs
- Python not yet supported