Use torch.no_grad() and more garbage collection

aiserver.py

@@ -1094,6 +1094,7 @@ def generate(txt, min, max):
         else:
             gen_in = txt
 		
+        with torch.no_grad():
             genout = generator(
                 gen_in, 
                 do_sample=True, 
@@ -1126,6 +1127,8 @@ def generate(txt, min, max):
     
     # Clear CUDA cache again if using GPU
     if(vars.hascuda and (vars.usegpu or vars.breakmodel)):
+        del genout
+        gc.collect()
         torch.cuda.empty_cache()
     
     set_aibusy(0)