bump torch to <2.4.1

[eitanturok]

What does this PR do?

bump torch to <2.5

What issue(s) does this change relate to?

Before submitting

• Have you read the contributor guidelines?
• Is this change a documentation change or typo fix? If so, skip the rest of this checklist.
• Was this change discussed/approved in a GitHub issue first? It is much more likely to be merged if so.
• Did you update any related docs and document your change?
• Did you update any related tests and add any new tests related to your change? (see testing)
• Did you run the tests locally to make sure they pass?
• Did you run pre-commit on your change? (see the pre-commit section of prerequisites)

[eitanturok]

TODO: test with torch 2.3 image

[eitanturok]

• megablocks tests run on torch2.3, torch2.4
• use forks of grouped_gemm, stk that support torch2.4

[eitanturok]

Closing in favor of #145. That PR is on a different branch of megablocks while this is on a fork of megablocks. It is much easier to run tests from a branch, rather than a fork, of megablocks.