How can I run SageMaker Serverless Inference on a GPU instance?

Unfortunately GPU based inference isn't currently supported on SageMaker Serverless Inference. From the feature exclusions section of the serverless endpoints documentation:

Some of the features currently available for SageMaker Real-time Inference are not supported for Serverless Inference, including GPUs, AWS marketplace model packages, private Docker registries, Multi-Model Endpoints, VPC configuration, network isolation, data capture, multiple production variants, Model Monitor, and inference pipelines.

Link here: https://docs.aws.amazon.com/sagemaker/latest/dg/serverless-endpoints.html