See what the latest AI Tools from Intel can do to improve your AI development tasks and extend your coding capabilities. Expand the boundaries of the latest optimized models and frameworks driving AI efficiency, boosting scaling, and enhancing generative AI (GenAI) quantization and inference.

Built to open standards, Intel® Extension for PyTorch* and Intel® Extension for TensorFlow* increase productivity and unlock new features, using a new slate of optimizations, including improvements to the Intel® Xeon® 6 processor with P-cores, Intel® Arc™ B-series graphics, and Intel GPUs with built-in accelerators.

The session offers insights into adopting a common, scalable approach to large language models (LLM) across diverse platforms, using open standards solutions based on AI, machine learning, and GenAI platforms.

A full portfolio of proven tools simplifies and streamlines AI development. By taking advantage of the latest Intel® AI optimizations and technologies, developers ensure they have access to broad multiarchitecture compatibility and access to a powerful set of versatile AI tools.

Topics covered in the webinar include:

• Discover the techniques for getting optimal performance from PyTorch AI solutions.
• Get the most value from performance libraries for AI.
• Use neural compressor technology to optimize and reduce model size and increase inference speed.
• Increase productivity and improve development time with ready-to-use AI Tools containers.