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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Usage]: LogitProcessor vLLM 0.9.1 run the same prompt 50 times with batching, apply logitprocessor independently on each
- [RFC]: Replace list[list[int]] to numpy arrays to mitigate GC overhead.
- [Feature]: model meta in openai api endpoint should include more model information
- [Performance][Feature]: make DeepGEMM swapAB available for linear gemm
- [Feature]: Allow use of `vllm bench serve` without installing all vLLM requirements
- [Bug][LoRA]: Custom AR IMA during CG Capture with LoRA
- [Usage]: There is any performance benchmark between running vLLM server via docker image and python?
- [Bug]: Unhandled exception: N9deep_gemm11DGExceptionE.
- [RFC]: Publishing KVBlocks event with mm_hash
- [Installation]: No pre-built wheel available in 0.11.0
- Docs
- Python not yet supported