[3/N][Refactor] Move torchair_attention to torchair dir (#2017)

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

1. Move `torchair_attention` to `torchair` dir.
2. Make `AscendAttentionTorchairBackend` extend `AscendAttentionBackend`
to reduce duplicate methods.
3. Make `AscendTorchairMetadata` extend `AscendMetadata` to reduce
duplicate properties.

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

### How was this patch tested?


- vLLM version: v0.10.0
- vLLM main:
0933f9d518

---------

Signed-off-by: shen-shanshan <467638484@qq.com>
This commit is contained in:
Shanshan Shen
2025-08-19 10:25:22 +08:00
committed by GitHub
parent 2a763b8326
commit 83e0f41408
5 changed files with 23 additions and 74 deletions

View File

@@ -169,7 +169,9 @@ class AscendAttentionMetadataBuilder:
num_actual_tokens,
max_query_len,
enable_dbo_across_dp: bool = False,
is_only_prefill: bool = False):
is_only_prefill: bool = False,
*args,
**kwargs):
block_table = self.runner.input_batch.block_table[0].get_device_tensor(
)