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
- [RFC]: Replaceable Scheduler
- [RFC]: Model architecture plugins
- [Feature]: How to run the int4 quantized version of the gemma2-27b model
- [Bug]: PaliGemma detection task is failing
- [Installation]: Install a shared vllm package compatible with multiple GPU architectures
- [Bug]: multi lora request bug
- [Performance]: under performing in comparision of sglang
- [CORE] [QUANT] Support for GPTQModel (GPTQ) Dynamic (Variable) bit per layer/module
- [Bugfix] fix spec decode with cuda graph
- [Bug]: ValueError: The number of required GPUs exceeds the total number of available GPUs in the cluster.
- Docs
- Python not yet supported