From 3f96fcf64631a100904bb189859f9aa80e8a75d5 Mon Sep 17 00:00:00 2001
From: Vasiliy Kuznetsov <vkuzo@users.noreply.github.com>
Date: Fri, 30 Jan 2026 12:29:09 -0500
Subject: [PATCH] fix QERL attention import path (#33432)

Signed-off-by: vasiliy <vasiliy@fb.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
---
 vllm/model_executor/model_loader/reload/layerwise.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/vllm/model_executor/model_loader/reload/layerwise.py b/vllm/model_executor/model_loader/reload/layerwise.py
index 6629f5c5f..f7aaf8a67 100644
--- a/vllm/model_executor/model_loader/reload/layerwise.py
+++ b/vllm/model_executor/model_loader/reload/layerwise.py
@@ -7,9 +7,9 @@ from weakref import WeakKeyDictionary
 
 import torch
 
-from vllm.attention.layer import Attention, MLAAttention
 from vllm.config import ModelConfig
 from vllm.logger import init_logger
+from vllm.model_executor.layers.attention import Attention, MLAAttention
 from vllm.model_executor.layers.quantization.base_config import QuantizeMethodBase
 from vllm.model_executor.model_loader.weight_utils import default_weight_loader