Making GPU Failure Invisible: A Zero-Cost Fallback for LLM Inference on Kubernetes
How three things Kubernetes already does for free replaced a failover system I didn't want to write
Raeveen Pasupathy | Blog
Latest articles
Deep dive into Docker Model Runner
TL;DR: Docker Model Runner represents a paradigm shift in local AI development, bringing the familiarity and reliability of Docker workflows to large language model inference. Unlike traditional containerized solutions, it runs models directly on the...
Building & Hosting a Discord Bot on AWS
Discord is a pretty amazing Platform. We all have been envisioning a collaborative platform among your family & friends, at least vigorously during the Pandemic. Discord has been evolving across the industry faster than any other Chat Platform. Initi...
Goodbye Access Keys, Hello OIDC: Unleashing Secure CI/CD with AWS IAM Roles (OIDC)
We all have been in a situation where we were worried what if our AWS Access Keys or Secret Access Keys got leaked. I mean, what can go wrong right? Well, let’s hold on our thoughts over here. Let’s now assume we have 100 IAM Access Keys active curre...
Running scalable httpd service on AWS
Prerequisites An AWS Account Basic knowledge regarding EFS, ASG, LaunchConfig, ALB, and EC2. We’ll be using **t2.micro** instance type as it is under AWS Free Tier, but I will still use Spot Instance :D. We’ll be deploying our instances in **Publ...
How to use AWS CLI or any Custom Command using Terraform | Raeveen Pasupathy
If you’re currently working on building your own Terraform Module, congratulations 🎉. It is evident that some build-in Terraform Modules may not be sufficient for your business or personal use-cases — Hence, that is why you’re into building yourself...