[Multimodal][XPU]Enable vision attn backend for xpu platform (#27525)

Signed-off-by: Yan Ma <yan.ma@intel.com>
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Co-authored-by: Yejing Lai <yejing.lai@intel.com>
Co-authored-by: Guancheng Fu <110874468+gc-fu@users.noreply.github.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>

vllm/platforms/xpu.py

@@ -115,6 +115,12 @@ class XPUPlatform(Platform):
         device_props = torch.xpu.get_device_properties(device_id)
         return device_props.total_memory
 
+    @classmethod
+    def get_vit_attn_backend(cls, head_size: int, dtype: torch.dtype) -> _Backend:
+        from vllm.attention.backends.registry import _Backend
+
+        return _Backend.FLASH_ATTN
+
     @classmethod
     def inference_mode(cls):
         return torch.no_grad()