Amazon Deep Learning Base Qualcomm AMI (Amazon Linux 2)

• Deep Learning Base Qualcomm AMI (Amazon Linux 2) ${YYYY-MM-DD}

• Supported Amazon Service: Amazon EC2

• Operating System: Amazon Linux 2

• Compute Architecture: x86

• Linux Kernel: 5.10.210-201.852.amzn2.x86_64

• SDK Location: /opt/qai-sdk

• QTI Utils Location: /opt/qti-aic

• Platform SDK Version: 1.12.0.88

• Apps SDK Version: 1.12.0.87

• EBS volume type: gp3

• Python: python3.8

• Supported EC2 Instances: dl2q

• Query AMI-ID with Amazon CLI (example Region is us-east-1): 

  aws ec2 describe-images --region us-east-1 \
      --owners amazon \
      --filters 'Name=name,Values=Deep Learning Base Qualcomm AMI (Amazon Linux 2) ????????' 'Name=state,Values=available' \
      --query 'reverse(sort_by(Images, &CreationDate))[:1].ImageId' \
      --output text

[4/12/24] Audit Package Removal

• DLAMIs released between March 26,2024 (2024-03-26) and April 12, 2024 (2024-04-12) were shipped without the audit package. If you require this specific package for your logging and monitoring needs, please migrate your workflows to the latest DLAMI in order to consume those with the audit package installed.

• By default, the qaic-pytools are not enabled through the Qualcomm AI100 Apps SDK. In order to enable and create the qaic pip environment qaic-env please run the following commands:

• AI 100 Platform SDK updated from version 1.10.0.200 to version 1.12.0.88

• AI 100 Apps SDK updated from version 1.10.0.193 to version 1.12.0.87

• SDK Version 1.12 adds support for transformer decoder models such as Llama-2 and Starcoder

• Qualcomm AI 100 Platform image upgraded to 1.10.0.200

• Initial release of Deep Learning Base Qualcomm AMI (Amazon Linux 2) series.

  • Please refer to the official Qualcomm documentation for more information on the Platform and Apps SDK: https://quic.github.io/cloud-ai-sdk-pages/

  • Please refer to the official Amazon documentation to learn more about dl2q instances: DL2q instances.