ViewTube

 Primary role is to provide solution from ESXi, vCenter, Storage, On-Prem Kubernetes.
• Participate in Designing and Planning the Data center Migration from old VMware version to new
 version.
• Built and deployed Docker containers to break up monolithic app into micro services, improving 
 developer workflow, increasing scalability, and optimizing speed.
• Support of the Docker services and container issues.
• Worked on container orchestration tool Kubernetes.
• Managed Docker orchestration and Docker containerization using Kubernetes.
• Used Kubernetes to orchestrate the deployment, scaling and management of Docker Containers.
• Deep understanding of how Scaling, updating live Containers.
• Port forwarding and network routing in kubernetes.
• Build a robust high availability cluster. 
• Kubernetes deployments of clusters and maintenance of pods.

Videos

4:15

Does a Model Upgrade Wipe Out Your LLM Router's Cache? We Tried to Break It (llm-d)

2 views

3d ago

6:19

Same 4 Pods, 2.3× Faster: How llm-d Routes LLM Traffic (Real Lab, No GPU)

1 view

3d ago

5:02

How Many Pods Do You Need for an LLM? We Checked the Sizing Math on a Real Cluster

0 views

3d ago

4:48

A 30-Second Spike Became an Outage: Client Retries vs an LLM Service (Measured)

0 views

3d ago

4:31

Traffic Jumps 6×. Will Your LLM Autoscale? (CPU HPA vs Queue-Based KEDA, Measured)

0 views

3d ago

4:56

Can You Upgrade an LLM Without Users Seeing Errors? (8 Rollout Strategies Measured)

3 views

3d ago

5:57

4 Pods, Slower Than 1: Autoscaling LLMs on Kubernetes (HPA vs KEDA, Ep 3)

0 views

3d ago

5:41

The 30-Second Bug Hiding in Your Kubernetes Manifests (LLM on K8s, Ep 2)

2 views

3d ago

5:43

I Ran an LLM on Kubernetes. Both Models Got It Wrong. (Ep 1)

1 view

3d ago

9:00

The AI Stack Explained: 8 Layers Behind Every AI App

3 views

4d ago

Shorts

I autoscaled my LLM and it got 3× slower #shorts

2 views

A normal load balancer made our LLM servers 2.3× slower #shorts

5 views