Neural Compressor Model Hardware Deployment and Compatibility

[DGP1607]

Aims to clarify the HW deployment capabilities of Neural Compressor optimized models.

• Specifically I'd like to know if these models are optimized for specific architectures such as x86 or if they are compatible with a wide range of HW (such as ARM) platforms.
• Are there any known issues or limitations when deploying optimized models on non-x86 architectures such as ARM, RISC-V, or others?
• What are Deployment Considerations for Non-x86 Platforms ?
• Understanding the HW compatibility will help assess the potential deployment scenarios for our models.