Refactor AscendMultiHeadLatentAttention (#2826)

Browse Source

### What this PR does / why we need it?
Register AscendMultiHeadLatentAttention as CustomOP, following vllm changes

### Does this PR introduce _any_ user-facing change?
N/A

### How was this patch tested?
CI passed with new added/existing test.


- vLLM version: main
- vLLM main:
b23fb78623

---------

Signed-off-by: Icey <1790571317@qq.com>

...

This commit is contained in:

Icey

2025-09-10 11:26:11 +08:00

committed by GitHub

parent 168ad600b5

commit aa4d2a91ed

4 changed files with 170 additions and 48 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

0

vllm_ascend/models/layers/__init__.py Normal file