electriclilies commented on pull request #8126: URL: https://github.com/apache/tvm/pull/8126#issuecomment-854120045
@mbrookhart I think` fake_quantization_to_affine_space` and `fake_quantization_to_integer` are the best options. I slightly prefer`fake_quantization_to_integer` because it's a bit more concise. Also, I did a quick google search and I think that the term affine space is used when talking about quantization in physics, but I didn't see any references to it in computer science literature. The only thing that comes up if you search "affine space" is stuff about vector spaces, and if you search "quantization affine space" you get physics papers. So I think if we do use the term affine space, we should be careful to explain what we mean by it in code comments and documentation since it's not a term that is commonly used. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected]
