TT - Forge

TT-Forge is an open-source MLIR-based compiler stack developed by Tenstorrent for compiling, optimizing, debugging, and extending machine learning models on custom silicon and Tenstorrent hardware. It integrates with major frameworks like PyTorch, TensorFlow, and ONNX, is modular and extensible, and includes a suite of supporting tools for performance analysis and optimization. TT-Forge is ideal for developers and AI engineers working with custom AI hardware who need flexible, high-performance model deployment and optimization solutions.