Hacker News Reader

Not sure I understand that question, is versioning the biggest problem no, but it costs nothing to keep semver and prevent production headaches later.

If you meant inference speed then yeah it's a very big problem so it's good that they are addressing it.

what exact production headaches you are expecting by bump the number from 1.13 -> 2.0, while all existing codes keep working as before?

And how is it different from bumping 1.13 to 1.14, even if they named it 1.14?

The soft kind. Major versions are deeply ingrained as "possible backward-compatibility issues" in most engineers' brain. If you handle model development, evaluation and deployment yourself than sure you won't have any issues, but in a bigger organization you have to get people to switch and that version number will mean that everyone will ask the same "hang on this is a major version change?!" question every step of the way.

No? What would have given you that impression?

Oh, I see. You were trying to be dismissive.

Quite the non sequitur you have there.