Running Large Language Models (LLMs) locally is becoming increasingly important for developers who care about privacy, cost, latency, and offline access. Ollama makes this practical by providing a clean CLI and a simple HTTP API to run models like Llama, Mistral, Gemma, and more on your own machine. In this post, we’ll explore what the … Read more
In the world of system design, the statement ‘Redis is faster than Kafka’ is a common talking point,but it requires a closer look. Redis is a fast in memory data store used to keep data that needs quick access. It is commonly used for caching, message queues, session storage, and real-time analytics. Redis stores data … Read more
Ollama has quickly become one of the most convenient ways to run large language models locally.This guide covers the most important and practical Ollama commands that you can use daily. Install a Model The pull command downloads a model from the official Ollama registry. To install a model run the below command : Example : … Read more
In this tutorial, we will discuss step by step guide to install CUDA driver on Ubuntu 24.04 LTS or higher. We tested this using NVIDIA RTX 3060 12GB GPU on Ubuntu 24.04 LTS. First update the system by running the below commands : We need to disable Nouveau driver,Nouveau is an accelerated open-source graphics driver … Read more
Imagine teaching a computer not just once, but continuously like how humans learn throughout their life. That’s the big idea behind Nested Learning, a fresh approach from Google Research that could help AI models learn new things without forgetting what they already know. The Problem: Why AI Forgets Traditional AI models struggle with continual learning … Read more
In this tutorial we will discuss git bisect to find the commit that caused regression bug. Regression Bug A regression bug is an error that appears in software after a change like a new feature, update, or fix causing previously working functionality to break.It indicates the system has “regressed” in quality. This can happen in … Read more
In this tutorial, we will discuss how to use the FastSD MCP server to generate an image using LM Studio. Download and install FastSD FastSDCPU is an open-source tool that enables fast text-to-image generation with Stable Diffusion models on CPUs and Intel AI PCs, leveraging Latent Consistency Models and Adversarial Diffusion Distillation for speed. It supports … Read more
In this step-by-step guide, we will explore how to set up Keycloak for app-to-app authentication. Project In this demo, we are going to create a project named “Cool Project” . It has a FastAPI-based API server and client app. For app-to-app authentication/authorization, we will use the OAuth2 client credentials flow. OAuth 2.0 Client Credentials Flow … Read more
In this article, we discuss how to use the FastSD MCP server with the Claude desktop to access the NPU to generate images. Model Context Protocol(MCP) Let’s first understand the Model Context Protocol (MCP). Anthropic developed the Model Context Protocol (MCP). Anthropic officially announced and open-sourced the protocol in November 2024. The MCP protocol is … Read more
Base64 Decoder Tool is a must-have utility for developers, cybersecurity professionals, data analysts, and tech enthusiasts who work with encoded data. Whether you’re debugging APIs, processing encrypted strings, or decoding hidden messages, this tool offers a fast and reliable solution for turning base64-encoded strings back into their original format. Key Features of the Base64 Decoder … Read more