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 supported48 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Quark] Support online block-diagonal rotations in dense GEMM layers
- [Bug]: 100% cpu usage on 3 cores on every node when using ray distributed pipeline parallel
- [Feature]: Any plans to add nvidia/parakeet-tdt-0.6b-v3 to vllm?
- [Bug]: torch.AcceleratorError: CUDA error: an illegal memory access was encountered
- [Feature] Conditional prefix logging for stdout/stderr
- [RFC]: Replace `torch.cuda` API with `torch.accelerator` for better hardware compatiblity.
- [Frontend][Core][Tracing] Add token-level OTEL tracing for prod observability
- [RFC]: Optimize embedding task
- [Feature] Default EPLB num_redundant_experts to minimum valid value
- Flashrl
- Docs
- Python not yet supported