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 supported30 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- fix(#40004): [Feature]: Priority scheduling supports preemption of requests in the running queue by requests in the waiting queue
- [Metrics] Add per-request preemption histogram (vllm:request_num_preemptions)
- [KV Connector] Mooncake store: prefix-cache retention interval for sparse attention
- [Draft][Rust] Add video modality support for vllm-rs
- [Bug]: vllm server crashed when use "--kv-offloading-backend native --kv-offloading-size 300" in long context
- [Frontend] Reduce multimodal preprocessing cache contention
- [Model] Optimize Qwen3-VL image-only preprocessing with compact patches
- Add Orthrus model support
- [Rust Frontend] Support parallel_tool_calls
- fix(#38736): [Transformers v5] Tarsier2ForConditionalGeneration
- Docs
- Python not yet supported