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 supported36 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- add retention interval to OffloadingConnector
- Validate request indices and sampler sizes before engine work
- Require a PyAV build with the fixed IAMF parser
- Roll back mirrored multimodal cache entries after rejection
- Validate scale-out multimodal data before engine handoff
- Cap the cumulative length of realtime sessions
- [Rust Frontend] Support stop strings in the token generate route
- [Frontend] Add routed-experts prompt offset
- Revert "[Config] Update default `_max_num_batched_tokens` from 8192 to 16384" (#51726)
- [Quantization][CT] fix the mxfp4 inference for MiniMax-M3 with CT format.
- Docs
- Python not yet supported