[Bug]: Regression in LoRA Adapter loading speed between vllm 0.4.3 and 0.5.0 about vllm HOT 4 CLOSED

diff --git a/vllm/lora/models.py b/vllm/lora/models.py
index 3e828568..ad09ecc3 100644
--- a/vllm/lora/models.py
+++ b/vllm/lora/models.py
@@ -217,6 +217,8 @@ class LoRAModel:
         """Create a LoRAModel from a dictionary of tensors."""
         pin_memory = str(device) == "cpu" and is_pin_memory_available()
         loras: Dict[str, LoRALayerWeights] = {}
+        import time
+        a = time.time()
         for tensor_name, tensor in tensors.items():
             module_name, is_lora_a = parse_fine_tuned_lora_name(tensor_name)
             if module_name not in loras:
@@ -258,8 +260,12 @@ class LoRAModel:
                     loras[module_name].lora_b = loras[
                         module_name].lora_b.pin_memory()

+        b = time.time()
+        print("Loaded lora(s) in ", b - a)
+
         for lora in loras.values():
             lora.optimize()
+        print("Optimized lora(s) in ", time.time() - b)
         return cls(lora_model_id, rank, loras, scaling_factor=scaling_factor)

     @classmethod