fix typo llama routing issue in trtllm-gen moe (#3303)

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

## 📌 Description

Fix the typo in the
[trtllm_fused_moe_runner.cu:582](https://github.com/flashinfer-ai/flashinfer/blob/v0.6.11/csrc/trtllm_fused_moe_runner.cu#L582).
Before, the FC2 kernels are incorrectly dropped.

## 🔍 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.
-->


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

## Summary by CodeRabbit

* **Bug Fixes**
* Fixed per-token scaling configuration in the mixture of experts
inference engine to use the correct settings for optimal performance.

[![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/3303)

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

Signed-off-by: Siyuan Fu <siyuanf@nvidia.com>