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 supported3 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Usage]: how to use `vllm` to output code only
- [Bug]: FusedMoE kernel performance depends on input prompt length while decoding
- [Performance]: Results from the vLLM Blog article "How Speculative Decoding Boosts vLLM Performance by up to 2.8x" are unreproducible
- [Installation]: Request to include vllm==0.6.2 for cuda 11.8
- [Bug]: Out of Memory (OOM) Issues During MMLU Evaluation with lm_eval
- [Installation]: Build vllm environment error
- DistServe Prototype
- [Feature]: To adapt to the TTS task, I need to directly pass in the embedding. How should I modify it?
- [Bug]: Get meaningless output when run long context inference of Qwen2.5 model with vllm>=0.6.3
- [Bug]: undefined symbol: __nvJitLinkComplete_12_4, version libnvJitLink.so.12
- Docs
- Python not yet supported