Spaces:

lablab-ai-amd-developer-hackathon
/

rocmport-agentic

Runtime error

App Files Files Community

rocmport-agentic / artifacts /check /amd_developer_cloud_runbook.md

Nawangdorjay

Deploy ROCmPort AI — CUDA-to-ROCm migration scanner

f6e0440 verified 6 months ago

preview code

Raw History Blame Contribute Delete

1.26 kB

# 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.

	# 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.