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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Whisper LLM.generate has no HF generate_with_fallback (loops / empty EOT)
- [Frontend] Give API workers independent reuseport listeners
- [Feature][KVConnector][DSv4.1] Encoder-only prefill with NIXL P/D
- [Bug]: Multi-node TP=8 (2 nodes x 4 H200) hangs in ncclCommInitRank during startup — even local_rank ranks complete Init COMPLETE, odd ranks block in graph-connect phase
- [Bugfix][MoE] Handle missing DP metadata in the two-sided NVLink all2all
- [Attention][CPU] Run Zen CPU decoder prefill on zentorch SDPA
- [Refactor][Mamba] 1/N: Unify device-pointer tensors to uint64
- [Test][ToolParser] Regression test: required streaming does not crash on single closed tool without parameters
- [CI][Test] Use file:// rendezvous in MoE parallel_launch to fix EADDRINUSE flakes
- [Feature]: Request observer hook for the Rust frontend
- Docs
- Python not yet supported