🚀 Born v0.2.0 Released - First Go ML Framework with Zero-CGO GPU Acceleration

We're excited to announce Born v0.2.0 - a major milestone that makes Born the first Go ML framework with zero-CGO GPU acceleration!

What is Born?

Born is a modern deep learning framework for Go, inspired by Burn (Rust). Our philosophy: "Models are born production-ready".

• 🎯 Pure Go - No CGO, trivial cross-compilation
• 🚀 GPU Acceleration - Via WebGPU (zero external dependencies)
• 🔒 Type Safe - Generics-powered API
• 📦 Single Binary - Deploy ML models as standalone executables

v0.2.0 Highlights

123x GPU Speedup

New Features

• ✅ WebGPU Backend - GPU compute via go-webgpu
• ✅ WGSL Shaders - 12 GPU-accelerated operations
• ✅ Buffer Pooling - Efficient GPU memory management
• ✅ Graceful Fallback - Works on systems without GPU

Quick Example

import (
    "github.com/born-ml/born/autodiff"
    "github.com/born-ml/born/backend/cpu"
    "github.com/born-ml/born/nn"
)

func main() {
    backend := autodiff.New(cpu.New())

    model := nn.NewSequential(
        nn.NewLinear(784, 128, backend),
        nn.NewReLU(),
        nn.NewLinear(128, 10, backend),
    )
    // Train and deploy as single binary!
}

Roadmap

Get Involved

• ⭐ Star the repo
• 📖 Read CONTRIBUTING.md
• 💬 Ask questions in Q&A category
• 💡 Suggest features in Ideas category
• 🐛 Report bugs in Issues

Install:

go get github.com/born-ml/[email protected]

Questions? Use Discussions, not Issues! 🙏