Compile with Framework API and Deploy on EC2 Inf2
Contents
This document is relevant for: Inf1
Compile with Framework API and Deploy on EC2 Inf2#
Table of Contents
Description#
You can use a single inf2 instance as a development environment to compile and deploy Neuron models. In this developer flow, you provision an EC2 inf2 instance using a Deep Learning AMI (DLAMI) and execute the two steps of the development flow in the same instance. The DLAMI comes pre-packaged with the Neuron frameworks, compiler, and required runtimes to complete the flow. Development happens through Jupyter Notebooks or using a secure shell (ssh) connection in terminal. Follow the steps below to setup your environment.
Note
Model compilation can be executed on a non-inf2 instance for later deployment. Follow the same EC2 Developer Flow Setup using other instance families and leverage Amazon Simple Storage Service (S3) to share the compiled models between different instances.
Setup Environment#
1. Launch an Inf2 Instance#
Please follow the instructions at launch an Amazon EC2 Instance to launch an Inf2 instance, when choosing the instance type at the EC2 console. Please make sure to select the correct instance type. To get more information about Inf2 instances sizes and pricing see Inf2 web page.
When choosing an Amazon Machine Image (AMI) make sure to select Deep Learning AMI with Conda Options. Please note that Neuron Conda environments are supported only in Ubuntu 18 DLAMI and Amazon Linux2 DLAMI, Neuron Conda environments are not supported in Amazon Linux DLAMI.
After launching the instance, follow the instructions in Connect to your instance to connect to the instance
Note
You can also launch the instance from AWS CLI, please see AWS CLI commands to launch inf2 instances.
2. Set up a development environment#
Enable PyTorch-Neuron#
Important
- For successful installation or update to next releases (Neuron 1.20.0 and newer):
Uninstall
aws-neuron-dkmsby running:sudo apt remove aws-neuron-dkmsorsudo yum remove aws-neuron-dkmsInstall or upgrade to latest Neuron driver (
aws-neuron-dkms) by following the “Setup Guide” instructions.
Note
For a successful installation or update, execute each line of the instructions below separately or copy the contents of the code block into a script file and source its contents.
# Neuron is pre-installed on Deep Learning AMI (DLAMI), latest DLAMI version may not include latest Neuron versions
# To update to latest Neuron version, follow "Update to latest release" instruction on Neuron documentation
################################################################################################################
# To install or update to Neuron versions 1.19.1 and newer from previous releases:
# - DO NOT skip 'aws-neuron-dkms' install or upgrade step, you MUST install or upgrade to latest Neuron driver
################################################################################################################
# Install OS headers
sudo apt-get install linux-headers-$(uname -r) -y
# Install Neuron Driver
sudo apt-get install aws-neuronx-dkms --allow-change-held-packages -y
####################################################################################
# Warning: If Linux kernel is updated as a result of OS package update
# Neuron driver (aws-neuron-dkms) should be re-installed after reboot
####################################################################################
# Activate PyTorch
source activate
Note
For a successful installation or update, execute each line of the instructions below separately or copy the contents of the code block into a script file and source its contents.
# Neuron is pre-installed on Deep Learning AMI (DLAMI), latest DLAMI version may not include latest Neuron versions
# To update to latest Neuron version, follow "Update to latest release" instruction on Neuron documentation
################################################################################################################
# To install or update to Neuron versions 1.19.1 and newer from previous releases:
# - DO NOT skip 'aws-neuron-dkms' install or upgrade step, you MUST install or upgrade to latest Neuron driver
################################################################################################################
# Install OS headers
sudo yum install kernel-devel-$(uname -r) kernel-headers-$(uname -r) -y
# Install Neuron Driver
sudo yum versionlock delete aws-neuronx-dkms
sudo yum install aws-neuronx-dkms -y
####################################################################################
# Warning: If Linux kernel is updated as a result of OS package update
# Neuron driver (aws-neuron-dkms) should be re-installed after reboot
####################################################################################
# Activate PyTorch
source activate
Note
For a successful installation or update, execute each line of the instructions below separately or copy the contents of the code block into a script file and source its contents.
# Neuron is pre-installed on Deep Learning AMI (DLAMI), latest DLAMI version may not include latest Neuron versions
# To update to latest Neuron version, follow "Update to latest release" instruction on Neuron documentation
################################################################################################################
# To install or update to Neuron versions 1.19.1 and newer from previous releases:
# - DO NOT skip 'aws-neuron-dkms' install or upgrade step, you MUST install or upgrade to latest Neuron driver
################################################################################################################
# Install OS headers
sudo apt-get install linux-headers-$(uname -r) -y
# Install Neuron Driver
sudo apt-get install aws-neuronx-dkms --allow-change-held-packages -y
####################################################################################
# Warning: If Linux kernel is updated as a result of OS package update
# Neuron driver (aws-neuron-dkms) should be re-installed after reboot
####################################################################################
# Activate PyTorch
source activate aws_neuron_pytorch_p36
Note
For a successful installation or update, execute each line of the instructions below separately or copy the contents of the code block into a script file and source its contents.
# Neuron is pre-installed on Deep Learning AMI (DLAMI), latest DLAMI version may not include latest Neuron versions
# To update to latest Neuron version, follow "Update to latest release" instruction on Neuron documentation
################################################################################################################
# To install or update to Neuron versions 1.19.1 and newer from previous releases:
# - DO NOT skip 'aws-neuron-dkms' install or upgrade step, you MUST install or upgrade to latest Neuron driver
################################################################################################################
# Install OS headers
sudo yum install kernel-devel-$(uname -r) kernel-headers-$(uname -r) -y
# Install Neuron Driver
sudo yum versionlock delete aws-neuronx-dkms
sudo yum install aws-neuronx-dkms -y
####################################################################################
# Warning: If Linux kernel is updated as a result of OS package update
# Neuron driver (aws-neuron-dkms) should be re-installed after reboot
####################################################################################
# Activate PyTorch
source activate aws_neuron_pytorch_p36
3. Set up Jupyter notebook#
To develop from a Jupyter notebook see Jupyter Notebook QuickStart
You can also run a Jupyter notebook as a script, first enable the ML framework Conda or Python environment of your choice and see Running Jupyter Notebook as script for instructions.
This document is relevant for: Inf1