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
- [Frontend] Plugin for OpenAI server (prototype)
- [P/D][Feature] Support using NIXL together with PP
- [Bug]: vLLM crashes when using --enable-sleep-mode with Blackwell PRO 6000 GPUs
- [Feature]: Support `Phi4Flash` model in V1
- [Performance]: ROPE + KV-Cache-Write + pre-attn prepare-ops fusion
- [Bug]: type object 'GroupShape' has no attribute '__origin__' when trying to use with torch.compile
- [Bug]: VLLM V1 Engine crashes with KeyError when processing concurrent embedding requests
- [Bug]: Inductor fails to fuse pointwise ops with sequence parallelism + async TP
- [New Model]: https://github.com/facebookresearch/omnilingual-asr
- [Feature]: Default eplb num_redundant_experts to the lowest valid value if unspecified
- Docs
- Python not yet supported