ray_template/deployment_scripts/deploy-env.sh

#!/bin/bash

export WS_DIR=<workspace_dir>

# Get the first character of the hostname
first_char=$(hostname | cut -c1)

# Check if the first character is not "r"
if [[ $first_char != "r" ]]; then
        # it's not a cpu node.
    echo "Hostname does not start with 'r'."
    # Get the first seven characters of the hostname
    first_seven_chars=$(hostname | cut -c1,2,3,4,5,6,7)
    # Check if it is an ai node
    if [[ $first_seven_chars != "hawk-ai" ]]; then
                echo "Hostname does not start with 'hawk-ai' too. Exiting."
        return 1
    else
        echo "GPU node detected."
        export OBJ_STR_MEMORY=350000000000
        export TEMP_CHECKPOINT_DIR=/localscratch/$PBS_JOBID/model_checkpoints/
        mkdir -p $TEMP_CHECKPOINT_DIR
    fi
else
        echo "CPU node detected."
fi

module load bigdata/conda

export RAY_DEDUP_LOGS=0

export ENV_ARCHIVE=ray_env.tar.gz
export CONDA_ENVS=/run/user/$PBS_JOBID/envs
export ENV_NAME=ray_env
export ENV_PATH=$CONDA_ENVS/$ENV_NAME

mkdir -p $ENV_PATH

tar -xzf $WS_DIR/$ENV_ARCHIVE -C $ENV_PATH

source $ENV_PATH/bin/activate

export CONDA_ENVS_PATH=CONDA_ENVS