Results for “seedream”

Import object detection models from HuggingFace or NVIDIA NGC into a DeepStream pipeline with automated ONNX download, TensorRT engine build, custom parser, multi-stream benchmark, and PDF report generation.

Creates SageMaker endpoints (real-time or async) with autoscaling, CloudWatch alarms, and tagging enabled by default, then smoke-tests them before declaring success.

Plans and coordinates the deployment of a model to Amazon SageMaker AI, selecting the appropriate pathway (real-time, serverless, async, batch, or Bedrock CMI) based on model type, traffic, latency, and cost constraints.

Re-platforms a site to AEM Edge Delivery (or any clean front end) while keeping its current design near pixel-perfect. Recreates key pages as clean HTML/CSS, verifies each against the live site with a measured source-fidelity gate, then hands off for site-wide delivery.

Discovers, validates, or creates a SageMaker execution role before deploying or training, preventing IAM-related deployment failures.