zero gpu, thanks @cbensimon !

app.py

@@ -1,5 +1,6 @@
 import os
 import subprocess
+import spaces
 import torch
 
 import gradio as gr
@@ -15,6 +16,8 @@ from PIL import Image
 from transformers.image_transforms import resize, to_channel_dimension_format
 
 
+subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
+
 DEVICE = torch.device("cuda")
 PROCESSOR = AutoProcessor.from_pretrained(
     "HuggingFaceM4/VLM_WebSight_finetuned",
@@ -113,6 +116,7 @@ def render_webpage(
     return Image.open(output_path_screenshot)
 
 
+@spaces.GPU(duration=180)
 def model_inference(
     image,
 ):

pre-requirements.txt

@@ -1 +0,0 @@
-torch

requirements.txt

@@ -1,7 +1,4 @@
 playwright
 transformers
-torch
 packaging
 ninja
-einops
-flash-attn