Foundation model benchmarking tool. Run any model on any AWS platform and benchmark for performance across instance type and serving stack options.
Contributions:351 pushes, 6 branches in 6 months
An end-to-end MLOps pipeline that reads data from PrestoDB to train an ML model and deploy on SageMaker for batch and realtime inference.
Contributions:1 review, 3 PRs, 74 pushes in 3 months
mlopsprestodbsagemakersagemaker-pipelines