diff --git a/modules/LoRA.py b/modules/LoRA.py
index 0eb56b56..2eade078 100644
--- a/modules/LoRA.py
+++ b/modules/LoRA.py
@@ -9,9 +9,9 @@ from modules.models import reload_model
 
 
 def add_lora_to_model(lora_names):
-    if 'GPTQForCausalLM' in shared.model.__class__.__name__:
+    if 'GPTQForCausalLM' in shared.model.__class__.__name__ or shared.args.loader == 'AutoGPTQ':
         add_lora_autogptq(lora_names)
-    elif shared.model.__class__.__name__ in ['ExllamaModel', 'ExllamaHF']:
+    elif shared.model.__class__.__name__ in ['ExllamaModel', 'ExllamaHF'] or shared.args.loader == 'ExLlama':
         add_lora_exllama(lora_names)
     else:
         add_lora_transformers(lora_names)
@@ -66,15 +66,16 @@ def add_lora_autogptq(lora_names):
         logger.error("This version of AutoGPTQ does not support LoRA. You need to install from source or wait for a new release.")
         return
 
-    if len(lora_names) == 0:
-        if len(shared.lora_names) > 0:
-            reload_model()
+    if len(lora_names) == 0:        
+        reload_model()
 
         shared.lora_names = []
         return
     else:
         if len(lora_names) > 1:
             logger.warning('AutoGPTQ can only work with 1 LoRA at the moment. Only the first one in the list will be loaded.')
+        if not shared.args.no_inject_fused_attention:
+            logger.warning('Fused Atttention + AutoGPTQ may break Lora loading. Disable it.')
 
         peft_config = GPTQLoraConfig(
             inference_mode=True,