fix qwen3-vl

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

Author: wangxiyuan

vllm_ascend/patch/worker/patch_qwen3_vl.py

@@ -135,7 +135,6 @@ def __init__(
         if self.attn_backend not in {
                 AttentionBackendEnum.FLASH_ATTN,
                 AttentionBackendEnum.TORCH_SDPA,
-                AttentionBackendEnum.XFORMERS,
                 AttentionBackendEnum.ROCM_AITER_FA,
         }:
             raise RuntimeError(