- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
This standard release provides more opportunity for AI innovation. Developers can now optimize & deploy with ease across an expanded range of hardware and deep learning models.
Broader model and hardware support
- NEW: Support for Intel® 13th Gen Core Processor for desktop (code named Raptor Lake).
- NEW: Preview support for Intel’s discrete graphics cards, Intel® Data Center GPU Flex Series and Intel® Arc™ GPU for DL inferencing workloads for intelligent cloud, edge and media analytics workloads.
- NEW: Test your model performance with preview support for Intel® 4th Generation Xeon® processors (code named Sapphire Rapids).
- Reduced memory consumption when using Dynamic Input Shapes on CPU. Improves efficiency for NLP applications.
- Introducing Intel® FPGA AI Suite which enables real-time, low-latency, and low-power deep learning inference in this easy-to-use package
More portability and performance - See a performance boost straight away with automatic device discovery, load balancing & dynamic inference parallelism across CPU, GPU, and more.
- NEW: “Cumulative throughput” and selection of compute mode added to AUTO functionality, enabling multiple accelerators (e.g. multiple GPUs) to be used at once to maximize inferencing performance, adding to AUTO’s base functionality of automatic discovery, configuration
More Integrations- It’s simple to adopt and maintain your code. These updates require minimal code changes and aligns better with frameworks. Geared towards those who have not yet installed native OpenVINO.
- The recently updated OpenVINO Execution Provider for ONNX Runtime gives ONNX Runtime developers more choice for performance optimizations by making it easy to add OpenVINO.
- NEW: Accelerate PyTorch model inferencing with OpenVINO™ integration with ONNX Runtime for PyTorch (OpenVINO™ Torch-ORT). Now PyTorch developers can more seamlessly integrate with OpenVINO and get performance gains with less code changes.
- OpenVINO Integration with TensorFlow now supports more deep learning models & improved inferencing performance.
RESOURCES
Link Copied
0 Replies
Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page