fix: minor errors in cubin loader (#1295)

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

## 📌 Description

<!-- What does this PR do? Briefly describe the changes and why they’re
needed. -->

## 🔍 Related Issues

<!-- Link any related issues here -->

## 🚀 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

- [x] I have installed `pre-commit` by running `pip install pre-commit`
(or used your preferred method).
- [x] I have installed the hooks with `pre-commit install`.
- [x] 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/).

## 🧪 Tests

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

## Reviewer Notes

<!-- Optional: anything you'd like reviewers to focus on, concerns, etc.
-->

Author: yyihuang

flashinfer/decode.py

@@ -1788,15 +1788,6 @@ def run(
     run_return_lse = functools.partialmethod(run, return_lse=True)
 
 
-# todo(Yingyi): update the params list
-@functools.cache
-def get_trtllm_fmha_gen_module():
-    mod = trtllm_fmha_gen_module()
-    op = mod.build_and_load()
-    setup_cubin_loader(mod.get_library_path())
-    return op
-
-
 class TrtllmGenDecodeModule:
     def _paged_run(
         self,
@@ -1841,9 +1832,13 @@ def _plan(self, *args, **kwargs):
     def __init__(self):
         self._mod = trtllm_fmha_gen_module()
         self._op = self._mod.build_and_load()
-        from flashinfer.jit.cubin_loader import setup_cubin_loader
+        from flashinfer.jit.cubin_loader import (
+            setup_cubin_loader,
+            setup_metainfo_loader,
+        )
 
         setup_cubin_loader(self._mod.get_library_path())
+        setup_metainfo_loader(self._mod.get_library_path())
 
 
 @functools.cache