Assess
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?
Apache TVM is an open source machine learning compiler framework for CPUs, GPUs, and machine learning accelerators. It aims to enable machine learning engineers to optimize and run computations efficiently on any hardware backend. Evaluate TVM and implement a WASI-NN interface targeting the TVM runtime.