Update app.py

app.py

@@ -15,13 +15,13 @@ from PIL import Image
 from transformers import AutoProcessor, AutoModelForImageTextToText, TextIteratorStreamer, Qwen2_5_VLForConditionalGeneration
 from qwen_vl_utils import process_vision_info
 
-import subprocess
-subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
+#import subprocess
+#subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
 model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
     "lingshu-medical-mllm/Lingshu-7B",
     torch_dtype=torch.bfloat16,
-    attn_implementation="flash_attention_2",
+    #attn_implementation="flash_attention_2",
     device_map="auto",
 )