Update app.py

app.py

@@ -29,6 +29,8 @@ 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.set_float32_matmul_precision("highest")
 
 from diffusers import StableDiffusion3Pipeline, SD3Transformer2DModel, AutoencoderKL