Posts

Multi-Instance GPU is a way to securely partition/share GPU for CUDA applications, providing multiple users with separate GPU resources for optimal GPU utilization. MIG allows us to partition single GPU card into a maximum of 7 GPU instance. Below is the example of A100 40GB which is sharded into 8 memory slices and 7 compute slices. Each of the memory slice will contain 1/8th of the total vram and each of the compute slice will have 1/7th total amount of streaming multiprocessors i....

This post describe how to expose http service to outside world on port 80 without external load balancer. For an example here will be using dummy bookinfo application by istio. This application contains a product page service which we will be exposing on the port 80 of kubernetes node. To deploy the istio sample application, run the below command. kubectl apply -f https://raw.githubusercontent.com/istio/istio/release-1.23/samples/bookinfo/platform/kube/bookinfo.yaml For more details on sample bookinfo application check istio doc - https://istio....

Many times we as developers come across a scenario where we require a Kubernetes cluster for testing or for hosting some application. Minikube and kind clusters are good for the local setup, and I use them in my day to day development work on local systems, but when it comes to installing Kubernetes on cloud instances I usually prefer to have a stock/vanilla Kubernetes cluster installed using Kubeadm, it gives me a sense of having more control over the cluster....