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
- [RFC]: Peer-device expert tier: run a subset of routed experts on a second GPU in the same host (out-of-tree plugin first, then a small seam in RoutedExperts)
- [Bugfix][CPU] Handle strided tensors in GELU-tanh
- [Draft][RFC][MoE]: Support dispatcher-native token dropping for MoE expert capacity
- [Perf][DSv4.1] Prototype Engram to delayed mHC input fusion
- Stop non-output workers after collective RPC failures
- fix debug
- [Feature]: Explicitly trust a selected preload daemon to avoid checkpoint rescans on engine restart
- [RL] Support model-native rank-local destinations for NCCL M2N
- [BreakableGraph][Bugfix] Bailing V3: make KDA attention an eager break
- [Bugfix][Test] Run the FlashInfer prefill tests causally, like their reference
- Docs
- Python not yet supported