Self-promo
Scaling a model endpoint on Kubernetes with NVIDIA Dynamo
NVIDIA AI says its five-minute video walks through Dynamo deployment with scalable workers and an OpenAI-compatible endpoint.
TLDR
NVIDIA AI frames the video around a question for people already running a model endpoint: how can they scale it on Kubernetes? It describes a five-minute walkthrough of how NVIDIA Dynamo handles deployment with scalable workers and an OpenAI-compatible endpoint.
Combined views
6.8K
1 Source, first seen ago
