Run GitHub Actions on AWS g5.xlarge

Why this fits

• 4 vCPU and 16 GiB RAM — sized for workloads the default GitHub-hosted runners can't comfortably host, all on your own AWS account.
• Single-GPU inference tests, smaller LLM evals, video-encode pipelines.
• NVIDIA A10G for PyTorch / vLLM and other CUDA workloads, with drivers + CUDA pre-baked in the runner image.

.cirun.yml

.cirun.yml

1runners:
2  - name: aws-g5-xlarge
3    cloud: aws
4    instance_type: g5.xlarge
5    # Use AWS Deep Learning AMI GPU PyTorch on Ubuntu 22.04
6    # (Marketplace) for pre-installed CUDA + drivers, or the
7    # Cirun-published NVIDIA AMI.
8    machine_image: ami-04823729c75214919
9    labels:
10      - cirun-aws-g5-xlarge

Drop this in your repo root. The first workflow that requests the runner label spins this configuration up on your cloud account.