Containers

Sanjeev Ganjihal

Author: Sanjeev Ganjihal

Sanjeev Ganjihal is a Sr. Specialist Solutions Architect for Containers at AWS. Sanjeev specializes in Service Mesh, Platform Engineering, Generative AI, Prompt Engineering, GitOps, IAC, Autoscaling, Cost Optimization & Observability. He helps customers in modernizing their applications by transitioning to containerized solutions, implementing AWS best practices, and steering their journey through cloud transformation. He is actively spending time on integrating AI with cloud-native solutions, delving into the realms of generative AI, prompt engineering, and harnessing data on Kubernetes. Outside of work he likes playing cricket and spends his time with his family.

Train Llama2 with AWS Trainium on Amazon EKS

Introduction Generative AI is not only transforming the way businesses function but also accelerating the pace of innovation within the broader AI field. This transformative force is redefining how businesses use technology, equipping them with capabilities to create human-like text, images, code, and audio, which were once considered beyond reach. Generative AI offers a range […]

Optimize AZ traffic costs using Amazon EKS, Karpenter, and Istio

In the evolving cloud-native landscape, enterprises utilizing Amazon Elastic Kubernetes Service (Amazon EKS) often encounter challenges that hinder their pursuit of operational efficiency and cost-effectiveness. Notable among these challenges are the costs associated with Cross Availability Zone (AZ) traffic, with difficulties associated with achieving seamless scalability, hurdles in provisioning right-sized instances for nodes, and intricacies […]

Scalable and Cost-Effective Event-Driven Workloads with KEDA and Karpenter on Amazon EKS

In today’s cloud-native landscape, efficient management of event-driven workloads is essential for real-time data processing. Traditional autoscaling often falls short amidst unpredictable event volumes, leading to inefficiencies and increased costs. Amazon Elastic Kubernetes Service (EKS), which is a managed container orchestration platform and is well-suited for deploying container-based applications. By integrating Kubernetes Event-Driven Autoscaling (KEDA) […]

GPU sharing on Amazon EKS with NVIDIA time-slicing and accelerated EC2 instances

In today’s fast-paced technological landscape, the demand for accelerated computing is skyrocketing, particularly in areas like artificial intelligence (AI) and machine learning (ML). One of the primary challenges the enterprises face is the efficient utilization of computational resources, particularly when it comes to GPU acceleration, which is crucial for ML tasks and general AI workloads. […]

Maximizing GPU utilization with NVIDIA’s Multi-Instance GPU (MIG) on Amazon EKS: Running more pods per GPU for enhanced performance

With the Generative Artificial intelligence (GenAI) and machine learning (ML) surge, GPU-intensive tasks such as machine learning, graphics rendering, and high-performance computing are becoming increasingly prevalent. However, many of these tasks do not always require the full performance and resources of a high-end GPU. This underutilization of GPU resources leads to inefficiencies, increased costs, and […]

Deploy Generative AI Models on Amazon EKS

Introduction Generative Artificial Intelligence (Gen AI) is transforming the way businesses function and is accelerating the pace of innovation. In general, the AI field is changing the way businesses utilize technology. Generative AI technology involves tuning and deploying Large Language Models (LLM), and gives developers access to those models to execute prompts and conversations. Platform […]