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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: LMCache connector with use_native crashes the worker: no get_kv_events
- [Bugfix][Frontend] Reject an empty conversation in every renderer
- [Bugfix][KV Connector] Guard optional LMCache events hook
- [Bugfix][Frontend][Rust Frontend] Accept DeepSeek V4.1 reasoning effort aliases
- [Bugfix][Frontend] Listen on IPv4 and IPv6 when --host is unset
- [CI][AMD] Move the remaining legacy-only AMD groups into test_areas and regenerate test-amd.yaml
- [Bugfix] Keep client-written FT status keys when the engine core pushes status
- [RFC]: Module layout for the Mooncake P2P KV connector
- [Feature] Support box and ground decision primitives with GUI-Actor pointer-head models
- [Model] Support box and ground decisions with GUI-Actor
- Docs
- Python not yet supported