XLA

Why?

We need to convert models for specific architectures, which requires many heterogeneous toolchains. A standardized framework that enables seamless integration of AI models with various XPUs, ensuring interoperability across different hardware platforms would be very useful.

What?

XLA (Accelerated Linear Algebra) is an open-source compiler for machine learning. The XLA compiler takes models from popular frameworks such as PyTorch, TensorFlow, and JAX, and optimizes the models for high-performance execution across different hardware platforms including GPUs, CPUs, and ML accelerators.