resources:
  accelerators: A100:8  # 8x NVIDIA A100 GPU

num_nodes: 1  # Number of VMs to launch

# Working directory (optional) containing the project codebase.
# Its contents are synced to ~/sky_workdir/ on the cluster.
workdir: ~/torch_examples

# Commands to be run before executing the job.
# Typical use: pip install -r requirements.txt, git clone, etc.
setup: |
  pip install "torch<2.2" torchvision --index-url https://download.pytorch.org/whl/cu121

# Commands to run as a job.
# Typical use: launch the main program.
run: |
  cd mnist
  python main.py --epochs 1