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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: gpt-oss-120b MXFP4 + --enable-expert-parallel crashes at startup: modular MoE finalize allocates padded (3072) output for an unpadded (2880) expert result
- [Feature][DSpark]: Evaluate STS for online DSpark confidence alignment
- [Feature][DSpark]: Improve Adaptive DSpark Online Profiling
- [ROCm][Perf] Split MiniMax-M3 prefill index-score K loop
- [ROCm][Perf] Fold scalar KV scales in MiniMax-M3 sparse attention
- [Bugfix][Spec Decode] Apply suppress_tokens on the Gemma 4 MTP sparse path
- [Bugfix] Handle empty YAML config in `--config` parsing
- [ROCm][Perf] Kimi-K3 AMD MLA: fuse the q-a and kv-a RMSNorms
- [Bug]: Continuous Host Memory Growth / Possible Memory Leak with V2 Runner on Qwen3-14B and Qwen3-Rerank-4B
- Fix: Deprecated pylance warnings on using AsyncIterator with asynccontextmanager
- Docs
- Python not yet supported