Update app.py

app.py

@@ -76,12 +76,8 @@ def evaluate(
         if '\n\n' in out_str:
             break
 
-    gpu_info = nvmlDeviceGetMemoryInfo(gpu_h)
-    print(f'vram {gpu_info.total} used {gpu_info.used} free {gpu_info.free}')  
     del out
     del state
-    gc.collect()
-    torch.cuda.empty_cache()
     yield out_str.strip()
 
 examples = [
@@ -222,11 +218,6 @@ def chat(
                 out, state = model.forward(tokens, state_pre_1)
                 break
 
-    gpu_info = nvmlDeviceGetMemoryInfo(gpu_h)
-    print(f'vram {gpu_info.total} used {gpu_info.used} free {gpu_info.free}')  
-
-    gc.collect()
-    torch.cuda.empty_cache()
 
     chatbot[-1][1] = out_str.strip()
     history = [state, state_pre_0, all_tokens]