[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/worker/v2/model_runner.py

@@ -32,8 +32,7 @@ from vllm.v1.worker.gpu.sample.output import SamplerOutput
 
 from vllm_ascend.worker.v2.aclgraph_utils import AclGraphManager
 from vllm_ascend.worker.v2.attn_utils import (build_attn_metadata,
-                                              build_attn_state,
-                                              make_attention_mask)
+                                              build_attn_state)
 from vllm_ascend.worker.v2.input_batch import AscendInputBuffers
 from vllm_ascend.worker.v2.sample.sampler import AscendSampler
 from vllm_ascend.worker.v2.states import AscendRequestState, uva_wrapper
@@ -155,12 +154,6 @@ class NPUModelRunner(GPUModelRunner):
             num_scheduled_tokens,
             num_valid_tokens,
         )
-        attn_mask = make_attention_mask(
-            self.vllm_config,
-            attn_state,
-            self.dtype,
-            self.device,
-        )
 
         idx_mapping_list = [
             self.req_states.req_id_to_index[req_id] for req_id in req_ids
@@ -284,7 +277,6 @@ class NPUModelRunner(GPUModelRunner):
             slot_mappings=slot_mappings.to(torch.int32),
             kv_cache_config=self.kv_cache_config,
             decode_token_per_req=self.decode_token_per_req,
-            attn_mask=attn_mask,
             attn_state=attn_state,
         )