[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>

tests/ut/spec_decode/test_mtp_proposer.py

@@ -291,8 +291,6 @@ class TestMtpProposer:
 
         mock_runner = MagicMock()
         mock_runner.actual_seq_lengths_q = MagicMock()
-        mock_runner.attn_mask = MagicMock()
-        mock_runner.spec_attn_mask = MagicMock()
         mock_runner.attn_state = MagicMock()
         mock_runner.graph_pad_size = 0
         mock_runner.decode_token_per_req = MagicMock()
@@ -334,5 +332,3 @@ class TestMtpProposer:
         assert spec_common_attn_metadata.num_actual_tokens == total_num_tokens
         assert spec_common_attn_metadata.max_query_len == 8
         assert spec_common_attn_metadata.actual_seq_lengths_q == proposer.runner.actual_seq_lengths_q
-        assert spec_common_attn_metadata.attn_mask == proposer.runner.attn_mask
-        assert spec_common_attn_metadata.spec_attn_mask == proposer.runner.spec_attn_mask