Try:

Build, Train, and Deploy Models with PyTorch

Talks on core concepts like tensors and autograd. Learn to implement neural networks for computer vision, NLP, and deploy them to production environments.

Matching moments

Accelerating deep learning with cuDNN and Cutlass
01:47 MIN

Accelerating deep learning with cuDNN and Cutlass

Accelerating Python on GPUs

Visualizing model predictions with the Captum library
04:12 MIN

Visualizing model predictions with the Captum library

Confuse, Obfuscate, Disrupt: Using Adversarial Techniques for Better AI and True Anonymity

Using ONNX Runtime for lightweight model inference
02:50 MIN

Using ONNX Runtime for lightweight model inference

Serverless deployment of (large) NLP models

Four methods for creating or acquiring ONNX models
11:33 MIN

Four methods for creating or acquiring ONNX models

Making neural networks portable with ONNX

Using C-Cloudy AI kernels for generative AI performance
01:57 MIN

Using C-Cloudy AI kernels for generative AI performance

Unleashing the Full Potential of the Arm Architecture – Write Once, Deploy Anywhere

How the Linux Foundation supports the end-to-end AI stack
01:53 MIN

How the Linux Foundation supports the end-to-end AI stack

The Open Future of AI: Beyond Open Weights

Visualizing a CNN's computational graph with FMRI scan
08:29 MIN

Visualizing a CNN's computational graph with FMRI scan

Debugging Machine Learning Code

Tooling, hiring, and how to get involved
02:07 MIN

Tooling, hiring, and how to get involved

Developing an AI.SDK

Understanding the CUDA platform stack for Python developers
05:33 MIN

Understanding the CUDA platform stack for Python developers

CUDA in Python

Developing models with the Platform for AI (PAI)
07:08 MIN

Developing models with the Platform for AI (PAI)

Alibaba Big Data and Machine Learning Technology

Identifying common data inconsistencies in AI models
03:13 MIN

Identifying common data inconsistencies in AI models

Confuse, Obfuscate, Disrupt: Using Adversarial Techniques for Better AI and True Anonymity

Choosing secure alternatives to the Pickle model format
00:43 MIN

Choosing secure alternatives to the Pickle model format

A hundred ways to wreck your AI - the (in)security of machine learning systems

Understanding CUDA as a complete computing platform
02:34 MIN

Understanding CUDA as a complete computing platform

Coffee with Developers - Stephen Jones - NVIDIA

A practical demo of a character-level BERT model
06:38 MIN

A practical demo of a character-level BERT model

What do language models really learn

Classifying images with noisy data using FastAI
04:43 MIN

Classifying images with noisy data using FastAI

Getting Started with Machine Learning

Analyzing supply chain and framework security risks
04:35 MIN

Analyzing supply chain and framework security risks

A hundred ways to wreck your AI - the (in)security of machine learning systems

How developers can contribute to the open source CUDA ecosystem
03:04 MIN

How developers can contribute to the open source CUDA ecosystem

Coffee with Developers - Stephen Jones - NVIDIA

Running the server and demonstrating the API
01:40 MIN

Running the server and demonstrating the API

Build your backend using FastAPI

How developers can get started and contribute to AI
06:16 MIN

How developers can get started and contribute to AI

Google Gemma and Open Source AI Models - Clement Farabet

Providing a simplified lab environment for data scientists
02:10 MIN

Providing a simplified lab environment for data scientists

Industrializing your Data Science capabilities

Frameworks and resources for building GNNs
01:46 MIN

Frameworks and resources for building GNNs

Graph Neural Networks: What’s behind the Hype?

Using geometric deep learning for molecular data
07:17 MIN

Using geometric deep learning for molecular data

Geometric deep learning for drug discovery

Navigating the diverse mobile AI framework ecosystem
02:20 MIN

Navigating the diverse mobile AI framework ecosystem

Mobile AI Just Got Faster: What’s Coming for Developers on Arm

Leveraging specialized hardware like Tensor Cores
03:11 MIN

Leveraging specialized hardware like Tensor Cores

Accelerating Python on GPUs

Training and fine-tuning models with the TAO Toolkit
01:49 MIN

Training and fine-tuning models with the TAO Toolkit

Trends, Challenges and Best Practices for AI at the Edge

Boosting Python performance with the Nvidia CUDA ecosystem
05:12 MIN

Boosting Python performance with the Nvidia CUDA ecosystem

The weekly developer show: Boosting Python with CUDA, CSS Updates & Navigating New Tech Stacks

Using CuPy as a drop-in replacement for NumPy
01:25 MIN

Using CuPy as a drop-in replacement for NumPy

Accelerating Python on GPUs

A progressive approach to programming GPUs in Python
10:18 MIN

A progressive approach to programming GPUs in Python

Accelerating Python on GPUs

A spectrum of approaches for programming GPUs in Python
01:40 MIN

A spectrum of approaches for programming GPUs in Python

Accelerating Python on GPUs

Accelerating language support with numba-cuda and nupack
02:36 MIN

Accelerating language support with numba-cuda and nupack

CUDA in Python

Drop-in libraries like CuPy and cuNumeric for easy acceleration
02:11 MIN

Drop-in libraries like CuPy and cuNumeric for easy acceleration

Accelerating Python on GPUs

Advanced techniques for boosting inference performance
03:36 MIN

Advanced techniques for boosting inference performance

Trends, Challenges and Best Practices for AI at the Edge

Key milestones in the evolution of AI and GPU computing
02:44 MIN

Key milestones in the evolution of AI and GPU computing

AI Factories at Scale

Deploying models with TensorRT and Triton Inference Server
02:16 MIN

Deploying models with TensorRT and Triton Inference Server

Trends, Challenges and Best Practices for AI at the Edge

A look at upcoming Python GPU programming tools
01:33 MIN

A look at upcoming Python GPU programming tools

Accelerating Python on GPUs

Achieving maximum flexibility with PyCUDA and C kernels
01:00 MIN

Achieving maximum flexibility with PyCUDA and C kernels

Accelerating Python on GPUs

Matching Videos

From Model to Metal: An Open Source Stack for Accelerating Intelligence
17:18

From Model to Metal: An Open Source Stack for Accelerating Intelligence

Andrew Wafaa

CUDA in Python
21:02

CUDA in Python

Andy Terrel

The Open Future of AI: Beyond Open Weights
23:04

The Open Future of AI: Beyond Open Weights

Matt White

Build your backend using FastAPI
23:10

Build your backend using FastAPI

Ashmi Banerjee

Open Source: The Engine of Innovation in the Digital Age
27:53

Open Source: The Engine of Innovation in the Digital Age

Maxim Fateev, Jo Franchetti, Ankit Patel & Ivan Burazin

Alibaba Big Data and Machine Learning Technology
43:57

Alibaba Big Data and Machine Learning Technology

Dr. Qiyang Duan

A hundred ways to wreck your AI - the (in)security of machine learning systems
24:23

A hundred ways to wreck your AI - the (in)security of machine learning systems

Balázs Kiss

WWC24 - Ankit Patel - Unlocking the Future Breakthrough Application Performance and Capabilities with NVIDIA
22:07

WWC24 - Ankit Patel - Unlocking the Future Breakthrough Application Performance and Capabilities with NVIDIA

Ankit Patel

Making neural networks portable with ONNX
54:49

Making neural networks portable with ONNX

Ron Dagdag

Open Source AI, To Foundation Models and Beyond
31:05

Open Source AI, To Foundation Models and Beyond

Ankit Patel, Matt White, Philipp Schmid, Lucie-Aimée Kaffee & Andreas Blattmann

Confuse, Obfuscate, Disrupt: Using Adversarial Techniques for Better AI and True Anonymity
27:34

Confuse, Obfuscate, Disrupt: Using Adversarial Techniques for Better AI and True Anonymity

David vonThenen

Getting Started with Machine Learning
44:11

Getting Started with Machine Learning

Alexandra Waldherr

Google Gemma and Open Source AI Models - Clement Farabet
47:25

Google Gemma and Open Source AI Models - Clement Farabet

Unleashing the Full Potential of the Arm Architecture – Write Once, Deploy Anywhere
19:39

Unleashing the Full Potential of the Arm Architecture – Write Once, Deploy Anywhere

Andrew Waafa

Developing an AI.SDK
38:12

Developing an AI.SDK

Daniel Graff & Andreas Wittmann

Graph Neural Networks: What’s behind the Hype?
28:21

Graph Neural Networks: What’s behind the Hype?

Ekaterina Sirazitdinova

Serverless deployment of (large) NLP models
39:02

Serverless deployment of (large) NLP models

Marek Suppa

Accelerating Python on GPUs
22:18

Accelerating Python on GPUs

Paul Graham

AI Model Management Life Circles: ML Ops For Generative AI Models From Research to Deployment
25:41

AI Model Management Life Circles: ML Ops For Generative AI Models From Research to Deployment

Joy Chatterjee

Mobile AI Just Got Faster: What’s Coming for Developers on Arm
23:09

Mobile AI Just Got Faster: What’s Coming for Developers on Arm

Gian Marco Iodice

Debugging Machine Learning Code
50:37

Debugging Machine Learning Code

Svetlin Penkov

Geometric deep learning for drug discovery
42:56

Geometric deep learning for drug discovery

Noah Weber

Accelerating Python on GPUs
59:43

Accelerating Python on GPUs

Paul Graham

Accelerating Python on GPUs
24:39

Accelerating Python on GPUs

Paul Graham

Ranking Amazon Reviews by Quality with Pointwise Ratings learned from Pairwise Data
47:26

Ranking Amazon Reviews by Quality with Pointwise Ratings learned from Pairwise Data

Tanmay Bakshi

30 Golden Rules of Deep Learning Performance
46:30

30 Golden Rules of Deep Learning Performance

Anirudh Koul

Your Next AI Needs 10,000 GPUs. Now What?
29:52

Your Next AI Needs 10,000 GPUs. Now What?

Anshul Jindal & Martin Piercy

PySpark - Combining Machine Learning & Big Data
43:26

PySpark - Combining Machine Learning & Big Data

Ayon Roy

Coffee with Developers - Stephen Jones - NVIDIA
37:32

Coffee with Developers - Stephen Jones - NVIDIA

Stephen Jones

Efficient deployment and inference of GPU-accelerated LLMs​
23:01

Efficient deployment and inference of GPU-accelerated LLMs​

Adolf Hohl

Vectorize all the things! Using linear algebra and NumPy to make your Python code lightning fast.
57:49

Vectorize all the things! Using linear algebra and NumPy to make your Python code lightning fast.

Jodie Burchell

How to implement convenient Python bindings to C++
22:13

How to implement convenient Python bindings to C++

Konstantin Bespalov

The pitfalls of Deep Learning - When Neural Networks are not the solution
32:54

The pitfalls of Deep Learning - When Neural Networks are not the solution

Adrian Spataru & Bohdan Andrusyak

Unboxing the DeepFace
45:19

Unboxing the DeepFace

Sefik Serengil

Python: Behind the Scenes
25:29

Python: Behind the Scenes

Diana Gastrin

A beginner’s guide to modern natural language processing
56:46

A beginner’s guide to modern natural language processing

Jodie Burchell