Update app.py

app.py

@@ -9,8 +9,13 @@
 import os
 #subprocess.run(['sh', './torch.sh'])
 
+os.putenv('PYTORCH_NVML_BASED_CUDA_CHECK','1')
 os.putenv('TORCH_LINALG_PREFER_CUSOLVER','1')
-os.putenv('PYTORCH_CUDA_ALLOC_CONF','max_split_size_mb:128')
+alloc_conf_parts = [
+    'expandable_segments:True',
+    'pinned_use_background_threads:True'  # Specific to pinned memory.
+]
+os.environ['PYTORCH_CUDA_ALLOC_CONF'] = ','.join(alloc_conf_parts)
 os.environ["SAFETENSORS_FAST_GPU"] = "1"
 os.putenv('HF_HUB_ENABLE_HF_TRANSFER','1')