Vishwam Case Study 2: Massive Kubernetes Based Deployment
Vishwam develops an extensible emotional AI platform that allows for extraction of hidden and subtle information pertaining to intent, personality, and expression in the communication data streams of text, audio and video files. They develop a hybrid physics-based pseudo-AI network with the key value proposition being minimal amount of data required to create predictable emotional AI models. This self-learning platform can be accessed through Rest-API’s by any application for analyzing text, audio and video feeds in real time, to extract human emotions & personality information.
Vishwam needed a massively scalable solution (thousands of CPUs and 100s of GPUs). GCP Kubernetes was the optimal choice. Other requirements were dynamic POD scaling for scalability and cost management. The pipeline was not only responsible for handling highly specialized models, it also needed to manage massive amounts of data.
Trillo helped Vishwam design the Kubernetes architecture. It involved GCP services such as Kubernetes cluster, load balancers, Cloud SQL, Pub/Sub, and Cloud Storage. Trillo helped create a scheduler for pre-warming of PODs.
Vishwam got a highly scalable Kubernetes-based solution as a result of this effort.