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
- [Bugfix][Core] Abort requests still running at the --shutdown-timeout drain deadline
- [Kernel] Honor ND group FP8 input contract
- [Bugfix] Spawn workers when CUDA forward compatibility is enabled
- [Perf][Attention] Add bounded FP8 page expansion for native prefill
- [Spec Decode] Add an independent first-draft graph ceiling
- [Doc] Document streaming cancellation and KV cache reclamation in online server
- [Docs] Add drain shutdown section to Kubernetes deployment guide
- [Perf][Core] Bound block-hash slices to newly cached blocks
- [Bugfix][Structured Output] Preserve raw scores before grammar masking
- [KVConnector][MoRIIO] Keep the handshake listener alive on bad messages
- Docs
- Python not yet supported