NVIDIA Triton Inference Server
NVIDIA Triton Inference Server is an AWS technology referenced in recorded AI deployments; review the sample cases to see how it is applied.
3 cases3 catalog refs
Sample cases
EagleView reduces costs and processing time for aerial imagery extraction with Amazon SageMakerEagleView - Real Estate - United StatesCisco Webex Contact Center Topic Analytics: migrating LLM workloads to SageMaker InferenceCisco - Tech & Comms - United StatesForethought uses Amazon SageMaker multi-model endpoints to reduce generative AI inference costsForethought Technologies - Tech & Comms - United States