LLMs-from-scratch/setup/04_optional-aws-sagemaker-notebook/cloudformation-template.yml

AWSTemplateFormatVersion: '2010-09-09'
Description: 'CloudFormation template to create a GPU-enabled Jupyter notebook in SageMaker with an execution role and 
LLMs-from-scratch Repo'

Parameters:
  NotebookName:
    Type: String
    Default: 'LLMsFromScratchNotebook'
  DefaultRepoUrl:
    Type: String
    Default: 'https://github.com/rasbt/LLMs-from-scratch.git'

Resources:
  SageMakerExecutionRole:
    Type: AWS::IAM::Role
    Properties:
      AssumeRolePolicyDocument:
        Version: '2012-10-17'
        Statement:
          - Effect: Allow
            Principal:
              Service:
                - sagemaker.amazonaws.com
            Action:
              - sts:AssumeRole
      ManagedPolicyArns:
        - arn:aws:iam::aws:policy/AmazonSageMakerFullAccess
        - arn:aws:iam::aws:policy/AmazonBedrockFullAccess

  KmsKey:
    Type: AWS::KMS::Key
    Properties:
      Description: 'KMS key for SageMaker notebook'
      KeyPolicy:
        Version: '2012-10-17'
        Statement:
          - Effect: Allow
            Principal:
              AWS: !Sub 'arn:aws:iam::${AWS::AccountId}:root'
            Action: 'kms:*'
            Resource: '*'
      EnableKeyRotation: true

  KmsKeyAlias:
    Type: AWS::KMS::Alias
    Properties:
      AliasName: !Sub 'alias/${NotebookName}-kms-key'
      TargetKeyId: !Ref KmsKey

  TensorConfigLifecycle:
    Type: AWS::SageMaker::NotebookInstanceLifecycleConfig
    Properties:
      NotebookInstanceLifecycleConfigName: "TensorConfigv241128"
      OnCreate:
        - Content: !Base64 |
            #!/bin/bash
            set -e

            # Create a startup script that will run in the background
            cat << 'EOF' > /home/ec2-user/SageMaker/setup-environment.sh
            #!/bin/bash
            
            sudo -u ec2-user -i <<'INNEREOF'
            unset SUDO_UID

            # Install a separate conda installation via Miniconda
            WORKING_DIR=/home/ec2-user/SageMaker/custom-miniconda
            mkdir -p "$WORKING_DIR"
            wget https://repo.anaconda.com/miniconda/Miniconda3-4.7.12.1-Linux-x86_64.sh -O "$WORKING_DIR/miniconda.sh"
            bash "$WORKING_DIR/miniconda.sh" -b -u -p "$WORKING_DIR/miniconda" 
            rm -rf "$WORKING_DIR/miniconda.sh"

            # Ensure we're using the Miniconda conda
            export PATH="$WORKING_DIR/miniconda/bin:$PATH"

            # Initialize conda
            "$WORKING_DIR/miniconda/bin/conda" init bash
            source ~/.bashrc

            # Create and activate environment
            KERNEL_NAME="tensorflow2_p39"
            PYTHON="3.9"
            "$WORKING_DIR/miniconda/bin/conda" create --yes --name "$KERNEL_NAME" python="$PYTHON"
            eval "$("$WORKING_DIR/miniconda/bin/conda" shell.bash activate "$KERNEL_NAME")"

            # Install CUDA toolkit and cuDNN
            "$WORKING_DIR/miniconda/bin/conda" install --yes cudatoolkit=11.8 cudnn

            # Install ipykernel
            "$WORKING_DIR/miniconda/envs/$KERNEL_NAME/bin/pip" install --quiet ipykernel

            # Install PyTorch with CUDA support
            "$WORKING_DIR/miniconda/envs/$KERNEL_NAME/bin/pip3" install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu118

            # Install other packages
            "$WORKING_DIR/miniconda/envs/tensorflow2_p39/bin/pip" install tensorflow[gpu]
            "$WORKING_DIR/miniconda/bin/conda" install --yes tensorflow-gpu
            "$WORKING_DIR/miniconda/envs/tensorflow2_p39/bin/pip" install tensorflow==2.15.0
            "$WORKING_DIR/miniconda/bin/conda" install --yes setuptools tiktoken tqdm numpy pandas psutil

            "$WORKING_DIR/miniconda/bin/conda" install -y jupyterlab==4.0
            "$WORKING_DIR/miniconda/envs/tensorflow2_p39/bin/pip" install matplotlib==3.7.1

            # Create a flag file to indicate setup is complete
            touch /home/ec2-user/SageMaker/setup-complete

            INNEREOF
            EOF

            # Make the script executable and run it in the background
            chmod +x /home/ec2-user/SageMaker/setup-environment.sh
            sudo -u ec2-user nohup /home/ec2-user/SageMaker/setup-environment.sh > /home/ec2-user/SageMaker/setup.log 2>&1 &

      OnStart:
        - Content: !Base64 |
            #!/bin/bash
            set -e

            # Check if setup is still running or not started
            if ! [ -f /home/ec2-user/SageMaker/setup-complete ]; then
                echo "Setup still in progress or not started. Check setup.log for details."
                exit 0
            fi

            sudo -u ec2-user -i <<'EOF'
            unset SUDO_UID

            WORKING_DIR=/home/ec2-user/SageMaker/custom-miniconda
            source "$WORKING_DIR/miniconda/bin/activate"

            for env in $WORKING_DIR/miniconda/envs/*; do
                BASENAME=$(basename "$env")
                source activate "$BASENAME"
                python -m ipykernel install --user --name "$BASENAME" --display-name "Custom ($BASENAME)"
            done
            EOF

            echo "Restarting the Jupyter server.."
            CURR_VERSION=$(cat /etc/os-release)
            if [[ $CURR_VERSION == *$"http://aws.amazon.com/amazon-linux-ami/"* ]]; then
                sudo initctl restart jupyter-server --no-wait
            else
                sudo systemctl --no-block restart jupyter-server.service
            fi

  SageMakerNotebookInstance:
    Type: AWS::SageMaker::NotebookInstance
    Properties:
      InstanceType: ml.g4dn.xlarge
      NotebookInstanceName: !Ref NotebookName
      RoleArn: !GetAtt SageMakerExecutionRole.Arn
      DefaultCodeRepository: !Ref DefaultRepoUrl
      KmsKeyId: !GetAtt KmsKey.Arn
      PlatformIdentifier: notebook-al2-v2
      VolumeSizeInGB: 50
      LifecycleConfigName: !GetAtt TensorConfigLifecycle.NotebookInstanceLifecycleConfigName

Outputs:
  NotebookInstanceName:
    Description: The name of the created SageMaker Notebook Instance
    Value: !Ref SageMakerNotebookInstance
  ExecutionRoleArn:
    Description: The ARN of the created SageMaker Execution Role
    Value: !GetAtt SageMakerExecutionRole.Arn
  KmsKeyArn:
    Description: The ARN of the created KMS Key for the notebook
    Value: !GetAtt KmsKey.Arn