Modular's software stack will take care of all upstream integrations with AI frameworks, graph optimizations, and more, so you can focus on the differentiating features of your hardware. Own your code generation, performance and feature set. It's still early, but we're excited about the future.
Effortlessly extend your customer reach to all popular AI frameworks.
Autofusion and graph optimizations boost your hardware performance.
We support the ever-changing AI ecosystem, including the long-tail of operators and models.
You own your performance and can utilize the full capabilities of your hardware.
Your hardware “just works” often with only a few weeks of development.
- Integration with TensorFlow, PyTorch, plus variants like ONNX and TorchScript
- Full generality of models, including dynamic shapes, sparsity, custom ops, etc.
- Thousands of long-tail operators needed for compatibility
- Kernel fusion and other performance optimizations
- Automatic graph partitioning for distributed inference
- Standardized and hackable tools
- Modular provides a library of customizable kernels and microkernels written in Mojo 🔥
- Focus on the subset of the problem for your hardware
- Everything else just works — we provide fallback legacy long-tail kernels for compatibility
- Add new Mojo 🔥 kernels if you don’t find what you’re looking for, and enable your customers to the same
- Use Mojo 🔥 to directly inject MLIR, C/C++ or assembly code as needed
- Leverage standardized operators and tools to write high-level graph transformations