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 supported15 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Frontend] Enable drain shutdown mode for non-DP deployments
- [Feature][Attention][PCP] Support PCP (Prefill Context Parallel) with MLA
- [Hardware][AMD][Kernel] mori all2all backend integration
- [Model] Add support for Jina Embeddings V4
- [torch.compile] refactor config hashing to compile_factors and unify factor collection
- [Core] NGram GPU Implementation compatible with Async Scheduler
- [Feature] limit thinking tokens (hard limit)
- Support R-KV Cache Compression in vLLM
- DeepGemm MoE expert map support
- [Bug]: [V1] Testla T4 cannot work for V1
- Docs
- Python not yet supported