CUDA first

src/pipeline.py

@@ -42,12 +42,11 @@ def load_pipeline() -> Pipeline:
         local_files_only=True,
         torch_dtype=torch.bfloat16,
     )
-
+    pipeline.to("cuda")
     pipeline.transformer.to(memory_format=torch.channels_last)
     pipeline.transformer = torch.compile(pipeline.transformer)
     # pipeline.text_encoder.fuse_qkv_projections()
     # pipeline.vae = torch.compile(pipeline.vae)
-    pipeline.to("cuda")
     for _ in range(4):
         pipeline("cat", num_inference_steps=4)
     torch.cuda.empty_cache()