Key Updates includes:
Broader Model & Hardware Support
- Preview support for upcoming Intel® processors, including the Intel® Data Center GPU Flex Series and Intel® Arc™ GPU
- Support for 4th Gen Intel® Xeon Scalable processor (code named Sapphire Rapids)
- Reduced memory consumption when using dynamic shapes on CPU to improve efficiency of NLP applications
Portability and Performance
Introducing new performance hint “Cumulative throughput” in AUTO device plug-in, enabling multiple accelerators (e.g. multiple GPUs) to be used at once maximizing inferencing performance.
To download the latest release, do take a look at Intel® Distribution of OpenVINO™ Toolkit