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
- [Fusion] Residual stream for allreduce manual fusion
- [V1]_Support_multimodal_decoder_DBO_inputs
- [Bugfix][Reasoning] kimi_k3: return the reply as content when the think channel is skipped
- [RFC]: Holemiss: Selective Recovery of Partially Lost LLM Cache State
- [Bug] DeepSeek V4.1 Flash selects the last optional tool parameter based on JSON Schema property order, contradicting reasoning
- [Bugfix][Spec Decode] Keep the rejection-sampling residual nonzero in fp32
- [Bugfix][Quantization] Index INT8 MoE per-channel weight scales independently of act quant - #58570
- [Frontend]: Render requests: keep mm_metadata in the response when the tensors are omitted
- [Rust Frontend] add `/v1/messages` support
- [Bugfix][Distributed] Unpack misaligned packed tensors
- Docs
- Python not yet supported