# AMD Developer Cloud Runbook

This runbook validates `cuda_first_repo` on AMD Developer Cloud without executing untrusted code inside the ROCmPort AI Space.

## 1. Create an AMD GPU VM

Use an AMD Developer Cloud VM with an AMD Instinct GPU and ROCm-ready Docker support.

## 2. Build the ROCm container

```bash
docker build -f Dockerfile.rocm -t rocmport-cuda_first_repo .
```

## 3. Run a smoke check

```bash
docker run --rm -it \
  --device /dev/kfd \
  --device /dev/dri \
  --group-add video \
  --ipc=host \
  --network=host \
  --security-opt seccomp=unconfined \
  rocmport-cuda_first_repo
```

## 4. Run vLLM on ROCm

```bash
docker run --rm -it \
  --device /dev/kfd \
  --device /dev/dri \
  --group-add video \
  --ipc=host \
  --network=host \
  --security-opt seccomp=unconfined \
  -v "$PWD:/workspace/cuda_first_repo" \
  vllm/vllm-openai-rocm:latest \
  vllm serve Qwen/Qwen3-Coder-Next-FP8 --tensor-parallel-size 1
```

## 5. Capture benchmark metadata

```bash
rocm-smi --showproductname --showmeminfo vram --showuse
python scripts/collect_benchmark_result.py --output benchmark_result.json
```

Replace `data/benchmark_result.json` with the captured result before final submission.