Update app.py

app.py

@@ -1,8 +1,15 @@
 import spaces
 import os
 
+os.putenv('PYTORCH_NVML_BASED_CUDA_CHECK','1')
+os.putenv('TORCH_LINALG_PREFER_CUSOLVER','1')
+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")
+os.putenv('HF_HUB_ENABLE_HF_TRANSFER','1')
 
 import gradio as gr
 import numpy as np
@@ -34,8 +41,8 @@ torch.backends.cuda.matmul.allow_fp16_reduced_precision_reduction = False
 torch.backends.cudnn.allow_tf32 = False
 torch.backends.cudnn.deterministic = False
 torch.backends.cudnn.benchmark = False
-#torch.backends.cuda.preferred_blas_library="cublas"
-#torch.backends.cuda.preferred_linalg_library="cusolver"
+torch.backends.cuda.preferred_blas_library="cublas"
+torch.backends.cuda.preferred_linalg_library="cusolver"
 torch.set_float32_matmul_precision("highest")
 
 hftoken = os.getenv("HF_AUTH_TOKEN")