AI Hardware: Training, Inference, Devices and Model Optimization

preview_player
Показать описание

In Episode 10 of Mixture of Experts we are talking all hardware all the time. Guest host Bryan Casey is joined by Volkmar Uhlig, Chris Hay, and Kaoutar El Maghraoui to explore the intricacies of AI hardware. Is Apple creating a pattern for the industry with their on device and cloud architecture? Tune in to hear the experts debate the details.

0:00 - Intro
1:40 - AI Hardware deep dive
30:47 - Model Optimization

The opinions expressed in this podcast are solely those of the participants and do not necessarily reflect the views of IBM or any other organization or entity.

  1. IBM Technology
  2. IBM
  3. IBM Cloud
  4. Anthropic
  5. Claude 3.5
  6. BirdSQL
Рекомендации по теме
AI Hardware: Training, 0:38:25

AI Hardware: Training, Inference, Devices and Model Optimization

The Hard Tradeoffs 0:14:11

The Hard Tradeoffs of Edge AI Hardware

What is AI 0:06:05

What is AI Inference?

A Hardware Prototype 0:01:00

A Hardware Prototype Targeting Distributed Deep Learning for On-Device Inference

Deep Learning Concepts: 0:05:58

Deep Learning Concepts: Training vs Inference

AI’s Hardware Problem 0:16:47

AI’s Hardware Problem

EdgeCortix: Energy-Efficient, Reconfigurable 0:29:32

EdgeCortix: Energy-Efficient, Reconfigurable and Scalable AI Inference Accelerator for Edge Devices

Hardware & Co-Design 0:24:37

Hardware & Co-Design | Joel Coburn, Junqiang Lan & Jack Montgomery

AI Inference Engine 0:10:29

AI Inference Engine for Edge devices

[One Min. Tech] 0:03:32

[One Min. Tech] Choosing a Deep Learning Inference Hardware

AI vs Machine 0:05:49

AI vs Machine Learning

Intel's Raymond Lo 0:02:40

Intel's Raymond Lo Shows How to Quickly Deploy AI Inference to Billions of Devices (Preview)

The AI Hardware 0:13:26

The AI Hardware Problem

Benchmarking AI Inference 1:01:35

Benchmarking AI Inference at the Edge

Why inference #ML 0:01:23

Why inference #ML on device? #shorts

Using Software + 0:10:33

Using Software + Hardware Optimization to Enhance AI Inference Acceleration on Arm NPU

The Coming AI 0:15:41

The Coming AI Chip Boom

MTIA - Meta's 0:03:31

MTIA - Meta's First-Generation AI Inference Accelerator | AI at Meta

Multi-stage inference with 0:10:39

Multi-stage inference with Edge Impulse/Tensorflow Lite - Raspberry Pi 4 Compute Module

Hardware Accelerators for 0:32:55

Hardware Accelerators for Machine Learning Inference

AI Inference is 0:10:05

AI Inference is ABOUT to CHANGE!!!

Artificial intelligence 0:00:24

Artificial intelligence

Accelerate Big Model 0:01:08

Accelerate Big Model Inference: How Does it Work?

Machine Learning Inference 0:22:13

Machine Learning Inference on Raspberry Pico 2040 via Edge Impulse

Комментарии
Автор

Nice discussion and observations on apple's distributed approach to AI safety, locally on the Mac or iPhone, remotely in Apple cloud and finally delegate to external APIs like GPT

SridharIyengar
Автор

What did Kaoutar El Maghraoui say starting at 10:30 about the 'math more free LLMs' research paper?

bwhit