Deep Learning hardware acceleration with AWS Inferentia

preview_player
Показать описание
In this video, I show you how to get started with AWS Inferentia, and Amazon EC2 Inf1 instances.

Follow me on:
  1. Julien Simon
  2. aws
  3. machine learning
  4. deep learning
  5. data science
  6. hardware
Рекомендации по теме
Deep Learning hardware 0:17:46

Deep Learning hardware acceleration with AWS Inferentia

Hardware Accelerator for 0:00:34

Hardware Accelerator for Convolutional Neural Network

Hardware acceleration for 0:15:52

Hardware acceleration for on-device Machine Learning

Nvidia CUDA in 0:03:13

Nvidia CUDA in 100 Seconds

Hardware Acceleration for 0:07:30

Hardware Acceleration for AI Workloads

A Systematic Approach 0:10:49

A Systematic Approach To Designing AI Accelerator Hardware

Lecture 11 - 0:45:22

Lecture 11 - Hardware Acceleration

Deep Neural Network 0:05:32

Deep Neural Network Hardware Accelerator on FPGA

SLIDE: Smart Algorithms 0:30:04

SLIDE: Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning with Beidi Chen...

[REFAI Seminar 10/24/22] 0:49:59

[REFAI Seminar 10/24/22] Towards Functional Safety of Deep Learning Hardware Accelerators

Hardware acceleration of 0:00:12

Hardware acceleration of CNN on FPGA using opencl - part2

tinyML Summit 2022: 0:28:16

tinyML Summit 2022: Next-Generation Deep-Learning Accelerators: From Hardware to System

The AI Hardware 0:13:26

The AI Hardware Problem

All about AI 1:02:35

All about AI Accelerators: GPU, TPU, Dataflow, Near-Memory, Optical, Neuromorphic & more (w/ Aut...

ICCKE 2022 - 0:14:21

ICCKE 2022 - Financial Market Prediction Using Deep Neural Networks with Hardware Acceleration

Jacinto 7 processors: 0:07:33

Jacinto 7 processors: application-specific hardware accelerators

691: A.I. Accelerators: 1:32:34

691: A.I. Accelerators: Hardware Specialized for Deep Learning — with Ron Diamant

Introduction to Machine 0:07:15

Introduction to Machine Learning Hardware Accelerators (Digital and In-Memory Computing)

CPU vs GPU: 0:07:32

CPU vs GPU: Why GPUs are more suited for Deep Learning? #deeplearning #gpu #cpu

Lecture 13 - 0:50:09

Lecture 13 - Hardware Acceleration Implemention

Deep learning accelerator 0:00:38

Deep learning accelerator for ADAS

Hardware Accelerators for 0:32:55

Hardware Accelerators for Machine Learning Inference

Cecile – Manager, 0:00:57

Cecile – Manager, Computer Vision / Machine Learning Hardware Acceleration

Boost AI Performance 0:00:41

Boost AI Performance With CPU Acceleration

Комментарии
Автор

Hi Julian, hope you are fine.
I have made a REST API with API Gateway, Lambda and sagemaker endpoint, the time that model take for inference is hardly 1sec, but the API on average takes about 5-9 secs, and sometimes can also take more than 30 secs.
SO, how to make it response fast.
Kindly, guide me to any relevant blog, or video.

Thanks a lot...

MuhammadAli-migg
Автор

Can we use Inferentia, for deploying Pytorch endpoints as REST APIs.Like by integrating with Lambda, and API Gateway..?
Thanks..

MuhammadAli-migg
Автор

Julien, tu ne fais plus de video/talk in Fr ? only in Eng ? Did you move ?

ericd.
Автор

Hi Julian:
Kindly help me with the following error:

UnexpectedStatusException: Error for Compilation job Failed. Reason: ClientError: CompilationError: Unable to compile model for ml_inf1:', 'Please implement aten::alias in native_ops/aten.py')

Thanks for any help...

MuhammadAli-migg