[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>
This commit is contained in:
LICO67373
2026-01-07 17:09:52 +08:00
committed by GitHub
parent 91790fd85a
commit 380f089fbf
21 changed files with 118 additions and 148 deletions

View File

@@ -1150,3 +1150,14 @@ def check_kv_extra_config(vllm_config):
_check(
"decode",
vllm_config.kv_transfer_config.get_from_extra_config("decode", {}))
def singleton(cls):
instances = {}
def get_instance(*args, **kwargs):
if cls not in instances:
instances[cls] = cls(*args, **kwargs)
return instances[cls]
return get_instance