technifyed

Arm Education via edX

Optimizing Generative AI on Arm Processors: from Edge to Cloud

Overview

Efficient AI is more than algorithms. This hands-on course shows you how to optimize GenAI workloads on real-world systems using techniques such as SIMD (SVE, Neon), low-bit quantization, and the optimized KleidiAI library. You will develop essential strategies and skills to build scalable, high-performance AI on edge and cloud-based platforms based on the most widespread processor architecture.

What you'll learn

  • You will learn how to optimize AI inference using Arm-specific techniques such as SIMD (SVE, Neon) and low-bit quantization. The course covers practical strate…

Syllabus 8

  1. Module 1:Challenges Facing Cloud and Edge GenAI Inference
  2. Understanding the limitations and constraints of AI inference in different environments.
  3. Module 2:Generative AI Models
  4. Exploring model architectures, training methodologies, and deployment considerations.
  5. Module 3:ML Frameworks and Optimized Libraries
  6. A deep dive into AI software stacks, including PyTorch, Llama.cpp, and Arm-specific optimizations.
  7. Module 4: Optimization for CPU Inference
  8. Techniques such as quantization, pruning, and leveraging SIMD instructions for faster AI performance.

Skills you'll practise

AI/ML InferenceMachine LearningMobile PhonesPruningGenerative Artificial IntelligenceAlgorithmsArtificial IntelligencePerformance EngineeringAutonomous SystemScalabilityPyTorch (Machine Learning Library)QuantizationInternet Of Things (IoT)Smartphone OperationData CentersAmazon Web ServicesSIMD

Advantages and disadvantages

Advantages

  • University courses you can audit for free, with lectures, readings and practice quizzes.
  • A verified certificate from the university if you pay for it.
  • Self-paced: start any time.
  • A clear syllabus (8 parts) you can see before you start.

Disadvantages

  • Graded assignments and the certificate need the paid track.
  • Audit access can expire a few weeks after the course ends.
  • Learning is free, but the certificate costs money.
  • Some parts (graded work, certificate) are paid.

Some points apply to every course of this kind; see how we rank.

Free to audit

  • Free: Choose "Audit this course" when you enrol: lectures, readings and practice are free.
  • Paid: Graded assignments and the verified certificate (Certificate $99). Audit access may end after the course closes.

Before you start

$3e

Taught by

  • Oliver GraingeAI Researcher
  • Kieran HejmadiSoftware and Academic Ecosystem Development Manager

Arm is in Tier 3: good universities, respected companies, nonprofits and well-known teachers of our institution ranking (76/100).

Similar courses

Compare these

Stanford University · YouTube

Stanford CS229: Machine Learning led by Andrew Ng | Autumn 2018

Led by Andrew Ng, this course provides a broad introduction to machine learning and statistical pattern recognition. Topics include: supervised learning (generative/discriminative learning, parametric/non-parametric learning, neural networks, support vector machines); unsupervised learning (cluster…

Free video21 videos, 28 hours

Stanford University · YouTube

Stanford CME295: Transformers and Large Language Models I Autumn 2025

This course explores the world of Transformers and Large Language Models (LLMs). You will learn the evolution of NLP methods, the core components of the Transformer architecture, along with how they relate to LLMs as well as techniques to enhance model performance for real-world applications. Throu…

Free video9 videos, 16 hours

Stanford University · YouTube

Transformers

Dive into the intriguing world of AI Transformers with this curated YouTube playlist. Featuring expert insights, educational content from leading organizations, and engaging discussions, this playlist keeps you informed about the latest breakthroughs in Transformer technology.

Free video16 videos, 17 hours

Stanford University · YouTube

Stanford CS25 - Transformers United

Stanford CS25: Transformers United Since their introduction in 2017, transformers have revolutionized Natural Language Processing (NLP). Now, transformers are finding applications all over Deep Learning, be it computer vision (CV), reinforcement learning (RL), Generative Adversarial Networks (GANs)…

Free video50 videos, 56 hours

Stanford University · YouTube

Stanford CS224N: Natural Language Processing with Deep Learning | 2023

Natural language processing (NLP) is a crucial part of artificial intelligence (AI), modeling how people share information. In recent years, deep learning approaches have obtained very high performance on many NLP tasks. In this course, students gain a thorough introduction to cutting-edge neural n…

Free video23 videos, 29 hours

Enter your email and the official page opens. Phone is optional.