---
library_name: pytorch
license: apache-2.0
tags:
  - foundation
  - amd
  - rocm
  - robotics
pipeline_tag: robotics
---

![](https://huggingface.co/AMD-PAVS-AI/smolVLA/resolve/main/smolvla.png)

# SmolVLA: Optimized for AMD ROCm

SmolVLA (vision-language-action) is a behavior-cloning policy from Hugging Face LeRobot for 6-DOF robot arm control. This repository packages inference for robot arm action prediction using **PyTorch**, exported and validated for **AMD ROCm** so it runs efficiently on AMD GPUs and CPUs.

This is based on the implementation of SmolVLA found [here](https://huggingface.co/lerobot/smolvla_base).
This repository contains configurations and scripts optimized for **AMD® ROCm™** platforms. You can use the [smolVLA AMD scripts](https://github.com/AMD-PAVS/physical_ai_sdk/blob/main/models/smolVLA) to reproduce results or export with custom configurations. More details on model performance can be found [here](#accuracy-pipeline).

---

## Task Overview

**Task:** Robot arm action prediction (vision-language-action)

**Dataset:** BlankHead/so101_redcube_greencloth_3cams (LeRobot format)

**Output metrics:** MAE, RMSE (per-joint and per-episode)

> **PyTorch note:** CPU runs FP32; GPU runs BF16. No NPU (VitisAI) path is available — `make setup-npu`, `make benchmark-npu`, and `make evaluate-npu` print an informational note and exit cleanly.

---

## AMD ROCm Optimization

This model export has been adapted and validated for **AMD Instinct™ / Radeon™ GPUs** running **ROCm**, as well as AMD CPUs. Key points:

- Validated backend: **PyTorch** (native ROCm HIP kernels), FP32 on CPU, BF16 on GPU.
- No code changes required versus the upstream SmolVLA implementation — only environment/runtime configuration differs.
- No NPU (VitisAI) fallback path is available for this model.

| Runtime | Precision | Backend | Hardware | Notes |
|---|---|---|---|---|
| PyTorch | FP32 | HIP (ROCm) | AMD CPU | — |
| PyTorch | BF16 | HIP (ROCm) | AMD Instinct™ / Radeon™ GPU | No NPU path available |

---

## Getting Started

For setup instructions, evaluation scripts, and custom configuration options, see the [smolVLA on GitHub](https://github.com/AMD-PAVS/physical_ai_sdk/blob/main/models/smolVLA).

---

## Model Details

**Model Type:** Vision-language-action policy for robot arm control

**Base Model:** `lerobot/smolvla_base`

**Model Stats:**
- Precision tested: FP32 (CPU), BF16 (GPU)
- Configurable runtime knobs: `rtc_config.enabled` (Real-Time Chunking), `num_steps` (flow-matching denoising passes per chunk), `n_action_steps` (actions consumed per chunk)

---

## Accuracy Pipeline

Open-loop offline evaluation is fully implemented: `make evaluate-<device>` runs inference on recorded dataset episodes and computes per-joint and per-episode MAE / RMSE against the recorded ground-truth actions. Lower is better for both metrics.

### Metrics Explained

| Metric | Description |
|--------|-------------|
| MAE | Mean Absolute Error — average absolute difference between predicted and ground-truth joint positions across all timesteps. Lower is better. |
| RMSE | Root Mean Squared Error — penalizes large deviations more heavily than MAE. Lower is better. |

### Accuracy Results

**Published Results** — Dataset: `BlankHead/so101_redcube_greencloth_3cams` (13 episodes, chunked_rtc mode):

<!-- accuracy-table-start -->
| Metric | Value |
|--------|-------|
| Average MAE | 3.9521 |
| Average RMSE | 7.7251 |
<!-- accuracy-table-end -->

**Per-joint breakdown:**

| Joint | Avg MAE | Avg RMSE |
|-------|---------|----------|
| shoulder_pan | 3.3654 | 5.1317 |
| shoulder_lift | 7.8224 | 14.0630 |
| elbow_flex | 4.9989 | 8.7409 |
| wrist_flex | 2.4138 | 3.4653 |
| wrist_roll | 2.6728 | 3.9475 |
| gripper | 2.4394 | 4.5340 |

---

## Dig Deeper

Want to explore the full evaluation scripts, config options, and other AMD-optimized model examples?

📂 **[View the full project on GitHub](https://github.com/AMD-PAVS/physical_ai_sdk/blob/main/models/smolVLA)**

The GitHub repository includes:
- Setup and prerequisites for ROCm environments
- Open-loop dataset evaluation with trajectory plots and comparison videos
- Latency benchmarking with Chrome trace output
- PEFT/LoRA-aware checkpoint loading and runtime chunking configuration