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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: torch.compile startup time logging not correct
- [Bug]: potential inconsistencies in shared memory due to lack of memory ordering guarantees
- [RFC]: Internal Process-level Fault Tolerance for vLLM
- [Feature]: AFD support load customer connect model from local path.
- [CI/Build] Skip spec decode tests using Triton backend
- [Bug]: AsyncTP pass has poor perf on B200
- [Feature]: WhisperX support
- [Feature]: Enabling draft model based speculative decoding for CPUs
- [Feature]: Improve DCP error messages
- [Feature]: Generalize RoutingMethodType for broader MoE routing control
- Docs
- Python not yet supported