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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Forward shutdown() in LMCacheConnectorV1 so EngineCore is not force-killed
- [Bugfix] Apply the layer q_scale only to FP8 queries in FlashInfer
- [Feature]: Stage-local eager DBO with pipeline parallelism in MRV2
- [Bugfix][RL] Destroy the previous NCCL communicator when the weight-transfer engine is re-initialized
- [Bugfix][Multimodal] Return 400 for corrupt audio that libsndfile recognises
- [Doc]: Architecture Overview page under Developer Guide is outdated in certain parts and does not match the current V1 architecture
- [Doc] Refresh architecture overview
- Relax and Update version constraints for numba, torch, and torchvision
- [Mooncake] Route KV transfers through a backend interface
- [Quantization][GLM-5.3] Let online quantization reach the BF16 attention projections
- Docs
- Python not yet supported