qai-cli

A CLI for the Qualcomm model MLOps pipeline — browse and download models from Qualcomm AI Hub, fine-tune them on custom datasets using SageMaker, validate inference, and prepare artifacts for Qualcomm hardware deployment.

Requirements

Python 3.13+
uv
AWS account with credentials configured (aws configure) when using qai-cli infra
AWS CDK CLI (npm install -g aws-cdk) when using qai-cli infra setup or qai-cli infra destroy

Installation

git clone <repo>
cd qai-cli
uv sync

Run commands with uv run qai-cli <command> or activate the venv first:

source .venv/bin/activate
qai-cli --help

Quick start

# 1. Create config.yaml in the current directory
qai-cli init

# 2. Edit config.yaml — at minimum set s3.bucket and sagemaker.role_name

# 3. Provision AWS infrastructure (S3 bucket + SageMaker IAM role).
#    This is the step that requires the AWS CDK CLI.
qai-cli infra setup

Configuration

qai-cli init writes a config.yaml in the current directory. The fields you must fill in before using the tool:

aws:
  region: us-east-1
  profile: default          # AWS CLI profile name

s3:
  bucket: your-unique-bucket-name

sagemaker:
  role_name: qai-cli-sagemaker-role

To provision an MLflow tracking server, set:

mlflow:
  mode: create
  tracking_server_name: your-tracking-server-name

To use an existing MLflow tracking server, set:

mlflow:
  mode: existing
  tracking_server_name: your-tracking-server-name

Commands

`init`

qai-cli init                  Write config.yaml
qai-cli init --output <path>  Write config to a custom path
qai-cli init --force          Overwrite an existing config file

`infra`

qai-cli infra setup                         Deploy the CDK stack
qai-cli infra setup --no-bootstrap          Deploy without running CDK bootstrap
qai-cli infra setup --cloudformation-execution-policy <arn> Set CDK bootstrap execution policy ARN
qai-cli infra status                        Show CDK stack/resource status
qai-cli infra destroy                       Destroy stack, retaining S3 data
qai-cli infra destroy --yes                 Destroy stack without confirmation
qai-cli infra destroy --delete-bucket-data  Destroy stack and delete S3 data

AWS permissions required

The IAM user or role running the CLI needs:

Action	Service
CreateBucket, DeleteBucket, PutObject, GetObject, ListBucket, DeleteObject	S3
CreateRole, GetRole, DeleteRole, AttachRolePolicy, DetachRolePolicy	IAM
CreateStack, UpdateStack, DeleteStack, DescribeStacks, DescribeStackEvents	CloudFormation
GetCallerIdentity	STS
CreateMlflowTrackingServer, DescribeMlflowTrackingServer, DeleteMlflowTrackingServer	SageMaker AI, when `mlflow.mode` is `create` or `existing`

AdministratorAccess covers all of the above.

2.9 KiB Raw Blame History