[Refactor] Fix AttentionMaskBuilder singleton and remove redundant pcp_prefill_mask (#4870)

## What this PR does / why we need it?

This PR fixes the `AttentionMaskBuilder` singleton initialization issue
introduced in PR #4779 and removes the unused `pcp_prefill_mask` field.

### Background

After PR #4779 made `AttentionMaskBuilder` a singleton with `@singleton`
decorator, the class constructor now requires a `device` parameter.
However, two initialization sites were still using the old parameterless
constructor, causing failures.

### Changes

1. **Fix singleton initialization**
- Fixed `AttentionMaskBuilder()` → `AttentionMaskBuilder(self.device)`
in `AscendMLAMetadataBuilder.__init__()`
- Fixed `AttentionMaskBuilder()` → `AttentionMaskBuilder(self.device)`
in `AscendAttentionMetadataBuilder.__init__()`

2. **Remove unused field**
- Removed `pcp_prefill_mask` field from
`AscendPrefillContextParallelMetadata` (never used in codebase)
   - Updated related test assertions

### Related

- Issue #5463
- PR #4779 (Unify all mask generation methods)
- PR #5389 (Make AttentionMaskBuilder singleton)

## Does this PR introduce _any_ user-facing change?

No. This is an internal refactoring.

## How was this patch tested?

- ✅ Local testing: No linter errors
- ✅ Unit tests for attention modules verified
- ⏳ CI pipeline

Signed-off-by: lico67373 <918688502@qq.com>
Co-authored-by: weijinqian0 <1184188277@qq.com>

vllm_ascend/spec_decode/eagle_proposer.py

@@ -222,8 +222,6 @@ class EagleProposer(VllmEagleProposer):
                 slot_mapping=self.runner.input_batch.block_table[0].
                 slot_mapping.gpu,
                 positions=self.runner.positions.gpu,
-                attn_mask=self.runner.attn_mask,
-                spec_attn_mask=self.runner.spec_attn_mask,
                 attn_state=self.runner.attn_state,
                 decode_token_per_req=self.runner.decode_token_per_req,
                 max_seq_len=0,
@@ -672,8 +670,6 @@ class EagleProposer(VllmEagleProposer):
             slot_mapping=common_attn_metadata.slot_mapping,
             actual_seq_lengths_q=self.runner.actual_seq_lengths_q,
             positions=common_attn_metadata.positions[token_indices],
-            attn_mask=self.runner.attn_mask,
-            spec_attn_mask=self.runner.spec_attn_mask,
             attn_state=self.runner.attn_state,
             decode_token_per_req=self.runner.decode_token_per_req,
             max_seq_len=0)
@@ -762,8 +758,6 @@ class EagleProposer(VllmEagleProposer):
             block_table_tensor=common_attn_metadata.block_table_tensor,
             slot_mapping=common_attn_metadata.slot_mapping,
             positions=common_attn_metadata.positions,
-            attn_mask=self.runner.attn_mask,
-            spec_attn_mask=self.runner.spec_attn_mask,
             attn_state=self.runner.attn_state,
             decode_token_per_req=self.runner.decode_token_per_req,
             num_computed_tokens_cpu=common_attn_metadata.