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
- ppc64le: Dockerfile and CI fix
- [Performance]: Suitable draft model for llama3.1 8b
- [Bug]: benchmark_serving.py generates different numbers of tokens at different runs
- [Kernel][Model] Varlen prefill + Prefill chunking support for mamba kernels
- [Bugfix] fix OpenAI API server startup with --disable-frontend-multiprocessing
- [Doc] Compatibility matrix for mutual exclusive features
- [Usage]: Best engine arguments for large batch inference
- [CI/Build][Misc] Comparing between block manager v1 and v2, under full prefix sharing and no prefix sharing case.
- [dbrx] refactor dbrx experts to extend FusedMoe class
- [Feature]: NotImplementedError: logprobs is not currently supported by the TPU backend
- Docs
- Python not yet supported