Runmat
Open-source runtime for math. Write MATLAB syntax, run on CPU + GPU automatically. Install via CLI, embed via NPM, or try instantly in the browser — no account needed.
Install / Use
/learn @runmat-org/RunmatREADME
What is RunMat?
With RunMat you write your math in clean, readable MATLAB-style syntax. RunMat automatically fuses your operations into optimized kernels and runs them on the best available hardware — CPU or GPU. On GPU, it can often match or beat hand-written CUDA on many dense numerical workloads.
It runs on whatever GPU you have — NVIDIA, AMD, Apple Silicon, Intel — through native APIs (Metal / DirectX 12 / Vulkan). No device management. No vendor lock-in. No rewrites.
x = 0:0.01:4*pi;
y0 = sin(x) .* exp(-x / 10);
y1 = y0 .* cos(x / 4) + 0.25 .* (y0 .^ 2);
y2 = tanh(y1) + 0.1 .* y1;
plot(x, y2);
Points in the graph below correspond to the number of elements in the x vector above:
Core ideas:
- MATLAB input language compatibility, not a new language
- Fast on CPU and GPU, with one runtime
- No device flags — Fusion automatically chooses CPU vs GPU based on data size and transfer cost heuristics
Ways to Use RunMat
The open-source runtime in this repo powers every RunMat surface:
<div align="center"> <table> <tr> <td align="center" width="20%"> <h3>🌐 Browser</h3> No install needed<br/><br/> Runs via WebAssembly + WebGPU.<br/> Your code never leaves your machine.<br/><br/> <a href="https://runmat.com/sandbox"><strong>Try now →</strong></a> </td> <td align="center" width="20%"> <h3>⌨️ CLI</h3> Open source (this repo)<br/><br/> Run <code>.m</code> files, benchmark,<br/> integrate into CI/CD.<br/><br/> <code>cargo install runmat</code> </td> <td align="center" width="20%"> <h3>📦 NPM</h3> Embed anywhere<br/><br/> Full runtime — execution, GPU,<br/> plotting — in any web app.<br/><br/> <a href="https://www.npmjs.com/package/runmat"><code>npm install runmat</code></a> </td> <td align="center" width="20%"> <h3>🖥️ Desktop</h3> Coming soon<br/><br/> Native IDE with local files<br/> and full GPU acceleration.<br/><br/> </td> <td align="center" width="20%"> <h3>☁️ Cloud</h3> Hobby tier available<br/><br/> Versioning, collaboration,<br/> team management.<br/><br/> <a href="https://runmat.com/pricing"><strong>Pricing →</strong></a> </td> </tr> </table> </div>✨ Features at a glance
-
MATLAB input language compatibility, not a new language
- Familiar
.mfiles, arrays, control flow - Many MATLAB / Octave scripts run with few or no changes
- Familiar
-
Fusion: automatic CPU+GPU choice
- Builds an internal graph of array ops
- Fuses elementwise ops and reductions into bigger kernels
- Chooses CPU or GPU per kernel based on shape and transfer cost
- Keeps arrays on device when that is faster
-
Modern CPU runtime
- Ignition interpreter for fast startup
- Turbine JIT (Cranelift) for hot paths
- Generational GC tuned for numeric code
- Memory-safe by design (Rust)
-
Cross-platform GPU backend
- Uses wgpu / WebGPU
- Supports Metal (macOS), DirectX 12 (Windows), Vulkan (Linux), WebGPU (browser)
- Falls back to CPU when workloads are too small for GPU to win
-
Async-capable runtime
- Evaluation is built on Rust futures — non-blocking by design, not bolted on
- GPU readback, interactive input, and long-running scripts never block the host
- Language-level
async/awaitwith cooperative tasks is on the roadmap - MATLAB has no equivalent — RunMat scripts can run interactively in a browser without freezing the page
-
WebAssembly target + NPM package
- The full runtime compiles to WASM and ships as part of this repo (
runmat-wasm) - Available as
runmaton NPM — embed execution, GPU acceleration, and plotting into any web app - GPU acceleration works in the browser via WebGPU
- Powers the browser sandbox — your code runs locally, never on a server
- The full runtime compiles to WASM and ships as part of this repo (
-
Plotting
- Interactive 2D and 3D plots
- Line, scatter, and surface plots supported today
- Some advanced plot types (box plots, violin plots) are still in progress
-
Open-source runtime
- The full runtime, GPU engine, JIT, GC, and plotting — everything in this repo — is MIT licensed
- Small binary, CLI-first design
📊 Performance
Up to 131x faster than NumPy and 7x faster than PyTorch on Monte Carlo simulations. Hardware: Apple M2 Max, Metal. Median of 3 runs.
| Paths (simulations) | RunMat (ms) | PyTorch (ms) | NumPy (ms) | NumPy ÷ RunMat | PyTorch ÷ RunMat | |--------------------:|-----------:|-------------:|-----------:|---------------:|-----------------:| | 250k | 108.58 | 824.42 | 4,065.87 | 37.44× | 7.59× | | 500k | 136.10 | 900.11 | 8,206.56 | 60.30× | 6.61× | | 1M | 188.00 | 894.32 | 16,092.49 | 85.60× | 4.76× | | 2M | 297.65 | 1,108.80 | 32,304.64 |108.53× | 3.73× | | 5M | 607.36 | 1,697.59 | 79,894.98 |131.55× | 2.80× |
</details> <details> <summary><strong>4K Image Pipeline</strong> — up to 10x faster than NumPy</summary>
| B | RunMat (ms) | PyTorch (ms) | NumPy (ms) | NumPy ÷ RunMat | PyTorch ÷ RunMat | |---|---:|---:|---:|---:|---:| | 4 | 142.97 | 801.29 | 500.34 | 3.50× | 5.60× | | 8 | 212.77 | 808.92 | 939.27 | 4.41× | 3.80× | | 16 | 241.56 | 907.73 | 1783.47 | 7.38× | 3.76× | | 32 | 389.25 | 1141.92 | 3605.95 | 9.26× | 2.93× | | 64 | 683.54 | 1203.20 | 6958.28 | 10.18× | 1.76× |
</details> <details> <summary><strong>Elementwise Math</strong> — up to 144x faster than PyTorch at 1B elements</summary>
| points | RunMat (ms) | PyTorch (ms) | NumPy (ms) | NumPy ÷ RunMat | PyTorch ÷ RunMat | |---|---:|---:|---:|---:|---:| | 1M | 145.15 | 856.41 | 72.39 | 0.50× | 5.90× | | 2M | 149.75 | 901.05 | 79.49 | 0.53× | 6.02× | | 5M | 145.14 | 1111.16 | 119.45 | 0.82× | 7.66× | | 10M | 143.39 | 1377.43 | 154.38 | 1.08× | 9.61× | | 100M | 144.81 | 16,404.22 | 1,073.09 | 7.41× | 113.28× | | 200M | 156.94 | 16,558.98 | 2,114.66 | 13.47× | 105.51× | | 500M | 137.58 | 17,882.11 | 5,026.94 | 36.54× | 129.97× | | 1B | 144.40 | 20,841.42 | 11,931.93 | 82.63× | 144.34× |
</details>On smaller arrays Fusion keeps work on CPU so you still get low overhead and a fast JIT.
See benchmarks/ for reproducible test scripts, detailed results, and comparisons against NumPy, PyTorch, and Julia.
🎯 Quick Start
Installation
# Quick install (Linux/macOS)
curl -fsSL https://runmat.com/install.sh | sh
# Quick install (Windows PowerShell)
iwr https://runmat.com/install.ps1 | iex
# Homebrew (macOS/Linux)
brew install runmat-org/tap/runmat
# Or install from crates.io
cargo install runmat --features gui
# Or build from source
git clone https://github.com/runmat-org/runmat.git
cd runmat && cargo build --release --features gui
Linux prerequisite
For BLAS/LAPACK acceleration on Linux, install the system OpenBLAS package before building:
sudo apt-get update && sudo apt-get install -y libopenblas-dev
Run Your First Script
# Start the interactive REPL
runmat
# Or run an existing .m file
runmat script.m
# Or pipe a script into RunMat
echo "a = 10; b = 20; c = a + b" | runmat
CLI Features
# Check GPU acceleration status
runmat accel-info
# Benchmark a script
runmat benchmark script.m --iterations 5 --jit
# Create a snapshot for faster startup
runmat snapshot create -o stdlib.snapshot
# View system information
runmat info
See CLI Documentation for the complete command reference.
Jupyter Integration
# Register RunMat as a Jupyter kernel
runmat --install-kernel
# Launch JupyterLab with RunMat support
jupyter lab
🧱 Architecture: CPU+GPU performance
RunMat uses a tiered CPU runtime plus a fusion engine that automatically picks CPU or GPU for each chunk of math. All of the components below are open source and live in this repository.
Key components
| Component | Purpose | Technology / Notes | | ---------------------- | ---------------------------------------- | ------
