This repo provides example notebooks how to deploy multiple Lora adapters with Sagemaker Studio.
Getting Started - Notebooks
- Deploy single model with optimized inference and DJL Serving – Only HF_MODEL_ID required
- Deploying 100's of Lora adapters with Lorax Server and Sagemaker
- Multi Adapter Deployment with DJL Serving
Blogs
- Efficient and cost-effective multi-tenant LoRA serving with Amazon SageMaker
- Overivew + LoRA Serving on Amazon SageMaker — Serve 100’s of Fine-Tuned LLMs For the Price of 1
- LoRA Exchange (LoRAX): Serve 100s of Fine-Tuned LLMs for the Cost of 1
Papers
Other Repos