aws-samples/sample-sagemaker-agentic-model-deployment

sagemaker-deploy

Stage any supported open-weight Hugging Face model directly into Amazon S3 and deploy it to an Amazon SageMaker AI real-time endpoint with a compatible vLLM or SGLang Deep Learning Container. Use for model hosting, endpoint creation, direct-to-S3 transfer,…

sagemaker-benchmark

Run a managed performance benchmark against a deployed Amazon SageMaker AI endpoint using SageMaker AI inference benchmarking (part of optimized GenAI inference recommendations; NVIDIA AIPerf under the hood). Measures TTFT, ITL, request-latency percentiles,…

sagemaker-optimize

Find an optimized serving configuration for a model with Amazon SageMaker AI inference recommendations, then deploy it and compare against a baseline benchmark. Covers both config search (best instance + serving knobs) and deep optimization (speculative…