Implement faster predict_y and generalised it to GPMC

[zhixiaozhu]

PR type: bugfix / enhancement / new feature / doc improvement

Related issue(s)/PRs:

Summary

Proposed changes

• ...
• ...
• ...

What alternatives have you considered?

Minimal working example

# Put your example code in here

Release notes

Fully backwards compatible: yes / no

If not, why is it worth breaking backwards compatibility:

PR checklist

• New features: code is well-documented
  • detailed docstrings (API documentation)
  • notebook examples (usage demonstration)
• The bug case / new feature is covered by unit tests
• Code has type annotations
• Build checks
  • I ran the black+isort formatter (make format)
  • I locally tested that the tests pass (make check-all)
• Release management
  • RELEASE.md updated with entry for this change
  • New contributors: I've added myself to CONTRIBUTORS.md

[zhixiaozhu]

Hi @uri-granta, @jesnie, I was trying to put together this PR but the CI kept failing. Could you please kindly help me to have a look if this was an issue by my change or the dev branch? I tired to run CI on the dev branch and it seemed to have failed with the same error. Many thanks.

[uri-granta]

Sorry I missed your comment! There were some typing issues exposed by third party library updates that have now been fixed (see #2094). Hopefully merging the latest develop will fix your problem.