PinnedShubham Mishra·May 25NVSentinel: Running your GPUs 24x7…It has been long since I wrote my experiences here, partly have been busy with customers in helping them achieve their Gen AI goals as much…
PinnedShubham Mishra·Nov 18, 2025SemiAnalysis GPUaaS ClusterMAX 2.0 ResultsIf you are into GPUaaS solutions as much as I am, you should absolutely read the complete report here. This requires a 500 USD subscription…
PinnedShubham Mishra·Sep 14, 2025Small Language Models and Agentic AI: A Match Made in HeavenTalking to a customer earlier last week in Asia, I learned quite a bit about the way enterprises are leveraging Small Language Models or…
PinnedShubham Mishra·Jul 20, 2025Why do you need Infiniband for Large Scale GPU Clusters…Last week I met a customer who wanted to use Llama 405B parameter model at FP8 with NVIDIA GPUs and wanted to know whether they should go…
Shubham Mishra·Mar 17NVIDIA’s Most Efficient Open Model (yet): Nemotron 3 Super Redefines Agentic AINVIDIA released Nemotron 3 Super just few days before GTC 2026 and for open model enthusiasts, it was a blast! There is a lot of uncover…
Shubham Mishra·Jun 20, 2025AMD’s Advancing AI — 2025 EventYes, I know I am a week and a day late for this post, but believe me when I say, I do not get any time to write my thoughts here cause of…
Shubham Mishra·May 2, 2025KV Cache for LLMs — Zero to HeroATTENTION is all you need, but KV cache is all what ATTENTION needs.
Shubham Mishra·Apr 19, 2025ROCm 6.4, released on April 11, 2025, represents AMD’s latest advancement in its open-source GPU…Core Architecture Improvements and Software Modularity
Shubham Mishra·Mar 1, 2025Local RAG with DeepSeek R1In my last write up I did a very simple setup where I ran DeepSeek on my ollama setup and used OpenWebUI to create “kind of” my own ChatGPT…
Shubham Mishra·Feb 25, 2025Personal ChatGPT using Ollama and OpenWebUIIn few simple steps and a GPU powered laptop we can have our own ChatGPT whether connected to internet or not. The process is fairly simple…A response icon1A response icon1