This repository is to store examples of deploying foundation models into Amazon SageMaker AI along with code to benchmark the model across different instance type. The benchmark result itself is purposefully not stored since it can vary with many factors. The repository is meant to provide samples on how the benchmark can be done, not the result.
The samples focus on deploying models into SageMaker AI for model hosting and benchmarking it with llmeter
The samples may deploy into SageMaker AI endpoints. Please refer to the pricing page. Different sample may use different components in SageMaker AI, so pay attention on what they deploy. They may also use other AWS services like Amazon S3 and others which have their own pricing.