cunn

Torch CUDA Neural Network Implementation for GPU-accelerated deep learning.

DecliningOpen SourceLow lock-in

Pricing

Free tier

Flat rate

Adoption

Cooling

License

Open Source

Data freshness

Aging · Jun 8, 2026

Overview

What is cunn?

cunn is a library that provides GPU acceleration for neural networks using CUDA, enabling faster training and inference in Torch. It's essential for developers working with large datasets or complex models who require high performance.

Key differentiator

cunn stands out as a specialized library within the Torch ecosystem, offering direct CUDA integration to accelerate neural network operations on GPUs, making it ideal for performance-critical applications.

Capability profile

Capability Radar

Ease of StartEcosystemValueMaturityFlexibilityScale Ready

Honest assessment

Strengths & Weaknesses

↑ Strengths

GPU acceleration using CUDA for faster neural network training and inference.medium

Integration with Torch, a scientific computing framework.medium

Supports various deep learning models and architectures.medium

↓ Weaknesses

Limited language support due to primary reliance on Luahigh

Lua is less popular compared to Python or JavaScript, limiting the developer community and available resources.

Complex setup for CUDA environmentmedium

Setting up CUDA can be challenging due to hardware and driver compatibility issues which may require significant effort to resolve.

Small and potentially inactive communityhigh

As an open-source project primarily in Lua, cunn might not have a large or active developer community for support and contributions.

Performance limitations on non-NVIDIA hardwaremedium

cunn relies heavily on CUDA which is optimized for NVIDIA GPUs. Performance on other GPU brands may be suboptimal or unsupported.

Fit analysis

Who is it for?

✓ Best for

Teams working with large datasets and complex neural network architectures who need GPU acceleration for faster training.

Projects requiring real-time inference capabilities on GPUs.

Developers already using Torch who want to leverage CUDA for performance improvements.

✕ Not a fit for

Projects that do not require or cannot utilize GPU resources.

Teams looking for cloud-based solutions without the need for local setup and maintenance.

Cost structure

Pricing

Free Tier

Available

Open source — free to use

Starts at

$0

Model

Flat rate

Enterprise

None

Performance benchmarks

How Fast Is It?

Ecosystem

Relationships

Next step

Get Started with cunn

Step-by-step setup guide with code examples and common gotchas.

View Setup Guide →