GPU, ML and real-time media for .NET. Everywhere it runs.
Write it once in C#. Run it on WebGPU, WebGL, WebAssembly, CUDA, OpenCL and CPU, in the browser and on the desktop. Backed by professional support your finance team can sign off on.
Native-class capability, from one C# codebase
Libraries that work alone and compose: GPU kernels feed ML inference, which feeds codecs and real-time networking, all driven from .NET.
SpawnDev.ILGPU
GPU compute in C#, in the browser or on the desktop.
SpawnDev.ILGPU.ML
Neural network inference and training in C#, on any GPU, in browser or desktop.
SpawnDev.SpawnJS
JSON-free JavaScript interop for .NET WebAssembly. No Blazor dependency.
SpawnDev.WebTorrent
Pure C# BitTorrent/WebTorrent client and server for desktop and browser.
SpawnDev.RTC
Cross-platform WebRTC for .NET: browser and desktop from a single API.
SpawnDev.AI
Run and serve local LLMs and image generation, on the desktop and in the browser.
An advantage, not a liability
One codebase, every target
The same C# runs in the browser and on the desktop. GPU kernels compile to WGSL, GLSL, Wasm, PTX and OpenCL C from one source.
Tested on real hardware
Every change is verified on each backend it touches, on real GPUs and real browsers, before release.
Built for throughput
Bulk data stays on the GPU or in JavaScript typed arrays. No hidden copies through the .NET heap.
Open source, no lock-in
Free for commercial use: SpawnDev code is MIT, and forks keep their original permissive licenses (details). You pay for support when you want it, never for the code.
GPU compute in C#, in the browser or on the desktop.
SpawnDev.ILGPU extends ILGPU, the .NET compiler that turns C# methods into GPU code, with three browser backends (WebGPU, WebGL and WebAssembly) and a SIMD CPU backend (Velocity) for the desktop. A kernel written for CUDA or OpenCL runs unchanged in a Blazor WebAssembly app and on the desktop, and the application picks the best available backend at run time. It ships as one NuGet package that brings the forked ILGPU compiler and SpawnDev.SpawnJS for browser interop.
More about SpawnDev.ILGPU// Registers every backend the environment offers:
// browser = WebGPU, WebGL, Wasm; desktop = CUDA, OpenCL, Velocity
using var context = await Context.CreateAsync(builder => builder.AllAcceleratorsAsync());
// Browser: WebGPU, then WebGL, then Wasm.
// Desktop: CUDA, then a discrete OpenCL GPU, then other OpenCL devices, then Velocity.
using var accelerator = await context.CreatePreferredAcceleratorAsync();
int length = 256;
using var a = accelerator.Allocate1D(Enumerable.Range(0, length).Select(i => (float)i).ToArray());
using var b = accelerator.Allocate1D(Enumerable.Range(0, length).Select(i => (float)i * 2f).ToArray());
using var c = accelerator.Allocate1D<float>(length);
var kernel = accelerator.LoadAutoGroupedStreamKernel<Index1D, ArrayView<float>, ArrayView<float>, ArrayView<float>>(VectorAdd);
kernel((Index1D)length, a.View, b.View, c.View);
await accelerator.SynchronizeAsync(); // wait for the GPU
float[] results = await c.CopyToHostAsync<float>(); // the one way to read results back in the browser
static void VectorAdd(Index1D i, ArrayView<float> a, ArrayView<float> b, ArrayView<float> c) => c[i] = a[i] + b[i];Shipping on SpawnDev?
Private tickets, response targets, a private GitHub tracker and a shared channel. Invoicing for businesses.