Learn AI

AI Deep Dive

Tag: cuda

  • Beyond Google: Other TPU and AI Accelerator Vendors

    Beyond Google: Other TPU and AI Accelerator Vendors While Google’s TPUs are a prime example of specialized AI hardware, the concept of a “TPU” (Tensor Processing Unit) as a dedicated ASIC (Application-Specific Integrated Circuit) for AI workloads has inspired other major tech companies and startups to develop their own custom AI chips. These are often Read more

  • Detailed Insights of TPU vs. GPU

    TPU vs. GPU Wars The “TPU vs. GPU wars” refer to the intense competition and ongoing debate over which type of specialized hardware accelerator is superior for Artificial Intelligence (AI) and Machine Learning (ML) workloads, particularly deep learning. While NVIDIA’s GPUs currently dominate the market, Google’s TPUs offer a compelling alternative with distinct advantages. 1. Read more

  • AI World Developments: Week of June 21, 2025

    AI World Developments: Week of June 21, 2025 This week has been particularly active in the AI landscape, marked by significant strides in generative AI, continued innovation in specialized hardware, intensified discussions around regulation and ethics, and the emergence of new applications transforming various industries. 1. Generative AI Continues to Transform and Diversify This week Read more

  • Understanding GPU Architecture (Detailed)

    Understanding GPU Architecture for Novices (Detailed) Imagine your computer needs to display a visually rich and dynamic scene, like a bustling city in a modern video game or a complex scientific visualization. The Central Processing Unit (CPU), while the “brain” of your computer, is optimized for a wide range of diverse tasks executed sequentially. Rendering Read more

  • How AMD GPUs Enable Deep Learning – Detailed

    How AMD GPUs Enable Deep Learning (for Novices) – Detailed Imagine training a computer to recognize patterns in vast amounts of data, like identifying diseases from medical images or understanding the sentiment behind millions of social media posts. Deep learning, a powerful subset of artificial intelligence, makes this possible. However, the sheer volume of calculations Read more

  • AMD vs. NVIDIA LLM Performance

    AMD vs. NVIDIA LLM Performance (May 2025) This article compares the performance of AMD and NVIDIA hardware when running Large Language Models (LLMs) as of May 2025, based on recent reports and trends. Key Factors Influencing LLM Performance VRAM (Video RAM) The size of the GPU’s memory is crucial for handling large LLMs. Larger models Read more

  • Implementing Locally running Mistral Chatbot with RAG

    Locally running Mistral Chatbot with RAG Let’s implement a local running chatbot with Mistral LLM using RAG to retrieve documents from a locally running Vector DB that also contains FAQs. Here’s a breakdown of the steps and the Python code to achieve this: Phase 1: Setting Up the Local Environment Install Dependencies: pip install transformers Read more

  • Using local LLM for Document Extraction

    Non-Cloud LLM for Document Extraction This guide explains how to use a non-cloud version of a pretrained Large Language Model (LLM) for document extraction, focusing on open-source models and local execution. Phase 1: Setting Up Your Local Environment 1. Hardware Requirements Ensure your system meets the following recommendations: CPU/GPU: An NVIDIA GPU with sufficient VRAM Read more

  • Tensor Reduction (Sum) with PyTorch and CUDA

    Tensor Reduction (Sum) with PyTorch and CUDA Tensor Reduction operations involve aggregating the values in a tensor across one or more dimensions to produce a tensor with a smaller number of dimensions (or a scalar). The sum reduction operation computes the sum of all elements (or elements along specified dimensions) of a tensor. CUDA significantly Read more

  • Tensor Multiplication (Element-wise) with PyTorch and CUDA

    Tensor Multiplication (Element-wise) with PyTorch and CUDA Element-wise Tensor Multiplication, also known as Hadamard product, involves multiplying corresponding elements of two tensors that have the same shape. Utilizing CUDA on a GPU significantly accelerates this operation through parallel processing. Code Example with PyTorch and CUDA import torch # Check if CUDA is available and set Read more