bugfix: Fix FusedMoeRunner does not exist error (flashinfer-ai#1424)

Fix `AttributeError: FusedMoeRunner does not exist` error when running
cutlass MoE.

Broken by flashinfer-ai#1201

<!-- .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.
-->

---------

Signed-off-by: Po-Han Huang <[email protected]>
Co-authored-by: Zihao Ye <[email protected]>

Author: nvpohanh

flashinfer/fused_moe/core.py

@@ -266,7 +266,7 @@ def gen_cutlass_fused_moe_sm100_module(use_fast_build: bool = False) -> JitSpec:
 
 @functools.cache
 def get_cutlass_fused_moe_sm100_module(use_fast_build: bool = False):
-    module = gen_cutlass_fused_moe_sm100_module(use_fast_build).build_and_load(
+    gen_cutlass_fused_moe_sm100_module(use_fast_build).build_and_load(
         class_name="FusedMoeRunner"
     )
 
@@ -329,14 +329,17 @@ def __init__(
             )
 
             if instance_key not in MoERunner.runner_dict:
-                MoERunner.runner_dict[instance_key] = module.FusedMoeRunner(
-                    x_dtype,
-                    weight_dtype,
-                    output_dtype,
-                    use_deepseek_fp8_block_scale,
-                    use_w4a8_group_scaling,
-                    use_mxfp8_act_scaling,
+                MoERunner.runner_dict[instance_key] = (
+                    torch.classes.fused_moe_sm100.FusedMoeRunner(
+                        x_dtype,
+                        weight_dtype,
+                        output_dtype,
+                        use_deepseek_fp8_block_scale,
+                        use_w4a8_group_scaling,
+                        use_mxfp8_act_scaling,
+                    )
                 )
+
             self.fused_moe_runner = MoERunner.runner_dict[instance_key]
 
         def get_valid_tactics(