[Refact.]: Refactor some leftover implementations of 300I DUO in the main branch. (#6425)

### What this PR does / why we need it?
- Replace the RoPE operator implementation.
- Refactor some leftover implementations of 300I DUO in the main branch.

### Does this PR introduce _any_ user-facing change?
NA
### How was this patch tested?

- vLLM version: v0.14.1
- vLLM main:
dc917cceb8

---------

Signed-off-by: Tflowers-0129 <2906339855@qq.com>
This commit is contained in:
Shaoxu Cheng
2026-02-02 16:12:04 +08:00
committed by GitHub
parent eeedf7c503
commit 460ea88276
7 changed files with 94 additions and 23 deletions

View File

@@ -19,10 +19,10 @@ import einops
import torch
import torch_npu
from vllm_ascend.ops.mm_encoder_attention import AscendMMEncoderAttention as _Base
from vllm_ascend.ops.mm_encoder_attention import AscendMMEncoderAttention
class AscendMMEncoderAttention310(_Base):
class AscendMMEncoderAttention310(AscendMMEncoderAttention):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)