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 supported2 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Config.__init__() got an unexpected keyword argument 'engine' api_server args
- [Feature]: Offline quantization for Pixtral-12B
- [CI/Build] Re-enabling Entrypoints tests on ROCm, excluding ones that fail
- [Bug]: Online serving failing for Phi-3-vision-128k-instruct
- Fix typical acceptance sampler with correct recovered token ids
- [MISC] add support custom_op check
- [Bugfix] Fix potentially unsafe custom allreduce synchronization
- [Misc]: Speed of serving Starcoder models
- [Bug]: Model load on 2 or 4-gpu A100 setup may cause default text encoding to be ascii, unless enforce_eager=True
- [Feature]: APC introspection interface
- Docs
- Python not yet supported