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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [XPU] Add tests for DCP and cache op
- [Test] Check supported-models docs against model registry
- [Test] Add unit tests for math_utils helpers
- [Test] Add tests for collection_utils helpers
- [Frontend][Responses] Accept input_audio content parts in user messages (#47659)
- [Frontend] support anthropic-defined client tools on /v1/messages
- [Bug]: Bidirectional NIXL: prefill-side request hangs in WAITING_FOR_REMOTE_KVS after its first D->P pull
- [Bugfix][NIXL] Fix bidirectional P-side hang after the first D->P pull
- [CPU] Move CPU-backend-only op wrappers into vllm/_cpu_ops.py
- [Feature]: [CI] Restore Ascend interface compatibility checks with locked test dependencies
- Docs
- Python not yet supported