SageMaker GPU Inference Cost Optimization

• A.Use a ml.p3.16xlarge instance with 8 GPUs.
• B.Use a SageMaker Serverless Inference endpoint.
• C.Use a Multi-Model Endpoint on a ml.g4dn.xlarge instance.
• ✓ D.Use a ml.p3.2xlarge instance with 1 GPU and enable automatic scaling.

Why D: Option D is the most cost-effective because it uses a single-GPU ml.p3.2xlarge instance, which matches the requirement that the model fits on one GPU, and enables automatic scaling to handle variable traffic without over-provisioning. This avoids paying for unused GPU capacity while still providing the necessary GPU acceleration for inference.

• ✓ A.Deploy an ml.p3.2xlarge instance with automatic scaling based on a custom metric like 'InvocationsPerInstance'
• B.Use a multi-model endpoint with ml.c5.4xlarge instances
• C.Use SageMaker Serverless Inference with a memory size of 6 GB
• D.Deploy a single ml.p3.16xlarge instance with a production variant

Why A: Option A is correct because deploying on an ml.p3.2xlarge instance with automatic scaling based on 'InvocationsPerInstance' allows the endpoint to handle bursty traffic up to 1000 requests per second while maintaining sub-100 ms latency. The GPU-accelerated p3 instance provides the necessary compute for a 5 GB deep learning model, and custom scaling on invocations per instance ensures that additional instances are provisioned quickly during traffic spikes without over-provisioning.

• ✓ A.Use GPU instances (e.g., ml.p3) for the endpoint.
• B.Use one endpoint per model to avoid interference.
• C.Use SageMaker Batch Transform for real-time predictions.
• ✓ D.Use SageMaker multi-model endpoints to host multiple models on the same instance.
• ✓ E.Use SageMaker Elastic Inference to attach GPU acceleration to a CPU instance.

Why A: Option A is correct because GPU instances like ml.p3 provide massively parallel compute capability that accelerates matrix operations common in deep learning models, enabling inference latencies under 10 ms. For real-time fraud detection, the GPU's high throughput and low latency are essential for processing thousands of transactions per second without bottlenecks.

• ✓ A.Instance type with GPU
• ✓ B.Create a SageMaker model with the inference code and model artifacts
• C.Batch transform job
• D.Production variant
• E.Training container image

Why A: Option A is correct because deploying a real-time inference endpoint with a large neural network that requires GPU acceleration necessitates selecting an instance type with a GPU, such as the ml.p3 or ml.g4dn series, to provide the parallel processing power needed for low-latency inference. Without a GPU instance, the model would fall back to CPU, leading to unacceptable inference times for large neural networks.