library_name: pytorch
license: other
tags:
- bu_auto
- android
pipeline_tag: other
StateTransformer: Optimized for Qualcomm Devices
StateTransformer is a transformer-based model designed for trajectory prediction in self-driving scenarios. It integrates rasterized map data, agent context, and temporal dynamics to generate accurate future trajectories.
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.
Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.
Getting Started
There are two ways to deploy this model on your device:
Option 1: Download Pre-Exported Models
Below are pre-exported model assets ready for deployment.
| Runtime | Precision | Chipset | SDK Versions | Download |
|---|---|---|---|---|
| ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | Download |
| TFLITE | float | Universal | TFLite 2.17.0 | Download |
For more device-specific assets and performance metrics, visit StateTransformer on Qualcomm® AI Hub.
Option 2: Export with Custom Configurations
Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:
- Custom weights (e.g., fine-tuned checkpoints)
- Custom input shapes
- Target device and runtime configurations
This option is ideal if you need to customize the model beyond the default configuration provided here.
See our repository for StateTransformer on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.driver_assistance
Model Stats:
- Model checkpoint: pretrained-mixtral-small
- Input resolution: 1x224x224x58, 1x224x224x58, 1x4x7
- Number of parameters: 90.7M
- Model size (float): 348 MB
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| StateTransformer | ONNX | float | Snapdragon® X Elite | 1155.042 ms | 183 - 183 MB | NPU |
| StateTransformer | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 680.781 ms | 97 - 5301 MB | NPU |
| StateTransformer | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 591.948 ms | 89 - 2116 MB | NPU |
| StateTransformer | ONNX | float | Snapdragon® X2 Elite | 817.45 ms | 202 - 202 MB | NPU |
| StateTransformer | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 499.081 ms | 215 - 232 MB | CPU |
| StateTransformer | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 1006.082 ms | 224 - 239 MB | CPU |
| StateTransformer | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 619.001 ms | 216 - 315 MB | CPU |
| StateTransformer | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 717.641 ms | 217 - 235 MB | CPU |
| StateTransformer | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 401.824 ms | 214 - 224 MB | CPU |
| StateTransformer | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 348.775 ms | 226 - 246 MB | CPU |
License
- The license for the original implementation of StateTransformer can be found here.
Community
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us.