EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

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

Browse Source 
### 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
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/platform.py
View File

@@ -218,7 +218,7 @@ class NPUPlatform(Platform):
if use_mla:
return "vllm_ascend.attention.mla_v1.AscendMLABackend"
elif use_torchair:
return "vllm_ascend.attention.attention_v1_torchair.AscendAttentionTorchairBackend"
return "vllm_ascend.torchair.torchair_attention.AscendAttentionTorchairBackend"
else:
return "vllm_ascend.attention.attention_v1.AscendAttentionBackend"