Intel NPU Acceleration Library 1.1 Adds New Model Support & Optimizations

Intel software engineers did a late Friday night release of the Intel NPU Acceleration Library v1.1, their Python library for tapping into the Intel Neural Processing Unit (NPU) found on the new Core Ultra (Meteor Lake) processors. This Python library makes it easier to interface with the Intel VPU/NPU kernel driver and in turn enjoying accelerated operations for AI.

With the new Intel NPU Acceleration Library 1.1 release, there is compilation improvements, Conv2D support, a function to clean the model cache to avoid out-of-memory situations, driver support for true quantization in eager mode, and other changes.

This is the first update to this Intel NPU Python library since the v1.0 milestone back in February.

Downloads and more details on this Intel NPU Acceleration Library update via GitHub.