修复W4A8 PP8崩溃问题

vllm/model_executor/layers/quantization/utils/w4a8_utils.py

-
 import torch
 import numpy as np
 
 try:
     from lightop import awq_marlin_repack_w4a8
-    use_lightop = True
+    use_lightop = False
 except Exception:
     use_lightop = False
 
@@ -90,4 +89,4 @@ def w4a8_weight_repack_impl(input):
             w_marlin_list.append(w_marlin_in)
         output = torch.stack(w_marlin_list, dim=0)
 
-    return output
\ No newline at end of file
+    return output