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
- [RFC][KV Cache] Implementation of programmable KV cache (#57103)
- [KV Connector] Windowed hidden-state export for ExampleHiddenStatesConnector
- [Bugfix][Parser] Hold partial parameter openers in streaming args
- [Bugfix][ROCm][MoRIIO] Support heterogeneous TP in READ mode for split KV heads and Mamba state
- [Bugfix][Frontend] Validate chat response JSON Schema keyword values
- [Bug]: Mooncake example proxy commits HTTP 200 before decode failures
- [Model] Support Decision 3.0 prefix_bidir attention (vllm-sr/d3-turbo)
- [Frontend] Support sanitize_control_tokens in chat templates
- [Bug]: HF3FS metadata server never frees pages; every save fails once the page pool is used up
- [Perf]: ~2x decode throughput regression for structured outputs since #45424 (apply_grammar_bitmask staging), not fixed by #49919
- Docs
- Python not yet supported