Espresso: Train and run Transformers directly on Apple's Neural Engine
A GitHub project called Espresso by Christopher Karani allows Transformer models to be trained and run directly on Apple's Neural Engine, bypassing the CPU and GPU. The tool could significantly speed up AI inference on Apple devices. The link garnered 14 points and 3 comments on Hacker News.
Comments
No comments yet
Comments
No comments yet โ be the first to weigh in ๐
No comments yet. Be the first!