fix: replace deprecated APIs: cute.make_fragment and cute.core.ThrMma (#3430)

<!-- .github/pull_request_template.md -->

## 📌 Description

`cute.make_fragment` and `cute.core.ThrMma` have been deprecated for
long and about to be removed. Replacing any occurrence with
`cute.make_rmem_tensor` and `cute.ThrMma` instead.

## 🔍 Related Issues

N/A

## 🚀 Pull Request Checklist

Thank you for contributing to FlashInfer! Before we review your pull
request, please make sure the following items are complete.

### ✅ Pre-commit Checks

- [ ] I have installed `pre-commit` by running `pip install pre-commit`
(or used your preferred method).
- [ ] I have installed the hooks with `pre-commit install`.
- [ ] I have run the hooks manually with `pre-commit run --all-files`
and fixed any reported issues.

> If you are unsure about how to set up `pre-commit`, see [the
pre-commit documentation](https://pre-commit.com/).

Basically NFC and mechanical change to replace the deprecated API.

## 🧪 Tests

- [ ] Tests have been added or updated as needed.
- [ ] All tests are passing (`unittest`, etc.).

API replacement - the existing test suite should still work

## Reviewer Notes

N/A


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

* **Refactor**
* Updated internal tensor construction methods in attention and GEMM
operations for improved code consistency.

<!-- review_stack_entry_start -->

[![Review Change
Stack](https://storage.googleapis.com/coderabbit_public_assets/review-stack-in-coderabbit-ui.svg)](https://app.coderabbit.ai/change-stack/flashinfer-ai/flashinfer/pull/3430?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack)

<!-- review_stack_entry_end -->

<!-- end of auto-generated comment: release notes by coderabbit.ai -->