Skip to content
1st Place

SAV.ai

NNPort redefines embedded engineering by fully automating the tasks that traditionally required specialized engineers, delivering an end-to-end autonomous development workflow.

Code Video Cerebral Valley

Core trick

Ports a PyTorch model to DSP, CUDA, or OpenCL targets, optionally pushing builds to Android over ADB for on-device debugging.

Tags

dev tools

Description

NNPort redefines embedded engineering by fully automating the tasks that traditionally required specialized engineers, delivering an end-to-end autonomous development workflow. Instead of replacing engineers outright, NNPort empowers them with advanced vibe debugging, step-by-step code exploration, and transparent logic tracing. This allows developers to understand, refine, and optimize individual code blocks with greater clarity, speed, and confidence.
a8nova/NNPort★ 32 forksPythonCreated Dec 7, 2025 · last push Dec 22, 2025

README excerpt

# NNPort

A web application for porting and debugging neural network architectures.

## Quick Start

### Prerequisites
- Python 3.9+
- Node.js 18+
- ADB (optional, for Android porting)

### 1. Setup Backend
```bash
# Create virtual env
python3 -m venv venv
source venv/bin/activate

# Install dependencies
pip install -r backend/requirements.txt

# Run Server
# IMPORTANT: Run from the project root (NNPort directory), NOT inside backend/
uvicorn backend.main:app --reload --port 8000
```

### 2. Setup Frontend
```bash
cd frontend
npm install
npm run dev
```

### 3. Usage
- Open `http://localhost:5173`
- Upload a source PyTorch model (must define `model` variable).
- Select Target (DSP, CUDA, OpenCL).
- Configure ADB if needed.
- Click "Start Porting".

Team