minor: some fix and cleanup for trtllm-gen mha (#1302)

<!-- .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

@@ -2065,7 +2065,6 @@ def trtllm_batch_decode_with_kv_cache_mla(
     block_tables: page_table of kv cache, [batch_size, num_pages]
     seq_lens: query_len
     max_seq_len: max sequence length for kv_cache
-    scale: model-specific scale of qk, default is 1.0
     out: output tensor, if not provided, will be allocated internally
     bmm1_scale: fused scale for mla bmm1 input.
     bmm2_scale: fused scale for mla bmm2 input.

include/flashinfer/trtllm/fmha/fmhaRunnerParams.h

@@ -22,6 +22,8 @@
 #include <cstdio>
 #include <cstring>
 
+#include "flashinfer/exception.h"
+
 ////////////////////////////////////////////////////////////////////////////////////////////////////
 
 // The attention mask types.
@@ -288,10 +290,7 @@ struct TllmGenFmhaRunnerParams {
         mMaskType = TrtllmGenAttentionMaskType::Custom;
         break;
       default:
-        // TLLM_THROW("ContextAttentionMaskType %d cannot be mapped to TrtllmGenAttentionMaskType",
-        //     static_cast<int>(maskType));
-        printf("ContextAttentionMaskType %d cannot be mapped to TrtllmGenAttentionMaskType",
-               static_cast<int>(maskType));
+        FLASHINFER_ERROR("Invalid attention mask type");
     }
     return *this;
   }