Hugging Face Partners With Intel, Launch Optimum Intel Library
Hugging Face has officially partnered with Intel to develop the Optimum Intel library, a library for using Hugging Face Transformers with Intel's Neural Compressor library.
Created on June 16|Last edited on June 16
Comment
Hugging Face and Intel have formally announced a partnership to drive improved performance for machine learning tasks on Intel hardware. The partnership comes via Hugging Face's Hardware Partner Program.
Hugging Face and Intel have previously partnered for smaller projects surrounding optimizing the workflow on Intel hardware, such as with low latency on Intel Xeon CPUs and support for training with Habana Gaudi processors.
Hugging Face Optimum Intel
The announcement comes with the launch of the Optimum Intel library, a library that acts as an interface between Hugging Face's Transformers library and Intel's own libraries for accelerated performance on their hardware. This expansion of the Optimum library allows users to easily access the Intel Neural Compressor library, tailor-built to support machine learning on Intel CPUs, for use with Hugging Face Transformers.
Find out more
Add a comment
Tags: ML News
Iterate on AI agents and models faster. Try Weights & Biases today.