bugfix: Fix trtllm moe launcher local_num_experts (#1398)

<!-- .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

- [ ] 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/).

## 🧪 Tests

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

## Reviewer Notes

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

Signed-off-by: Shu Wang <[email protected]>

Author: wenscarl

csrc/trtllm_fused_moe_kernel_launcher.cu

@@ -1062,7 +1062,7 @@ std::vector<at::Tensor> trtllm_fp4_block_scale_moe(
     hidden_states_scale_vec_size = (num_tokens * hidden_size) / hidden_states_scale.value().numel();
   }
   int weight_scale_vec_size =
-      (num_experts * intermediate_size * 2 * hidden_size) / gemm1_weights_scale.numel();
+      (local_num_experts * intermediate_size * 2 * hidden_size) / gemm1_weights_scale.numel();
   TORCH_CHECK(weight_scale_vec_size == 16 || weight_scale_vec_size == 32,
               "unsupported weight_scale_vec_size.");
   auto mDtypeWeights = weight_scale_vec_size == 16 ? btg::Dtype::E2m1 : btg::Dtype::MxE2m1;