Improve RAM<->VRAM memory copy performance in LoRA patching and elsewhere (#6490)

* allow model patcher to optimize away the unpatching step when feasible

* remove lazy_offloading functionality

* allow model patcher to optimize away the unpatching step when feasible

* remove lazy_offloading functionality

* do not save original weights if there is a CPU copy of state dict

* Update invokeai/backend/model_manager/load/load_base.py

Co-authored-by: Ryan Dick <ryanjdick3@gmail.com>

* documentation fixes requested during penultimate review

* add non-blocking=True parameters to several torch.nn.Module.to() calls, for slight performance increases

* fix ruff errors

* prevent crash on non-cuda-enabled systems

---------

Co-authored-by: Lincoln Stein <lstein@gmail.com>
Co-authored-by: Kent Keirsey <31807370+hipsterusername@users.noreply.github.com>
Co-authored-by: Ryan Dick <ryanjdick3@gmail.com>

invokeai/backend/onnx/onnx_runtime.py

@@ -6,6 +6,7 @@ from typing import Any, List, Optional, Tuple, Union
 
 import numpy as np
 import onnx
+import torch
 from onnx import numpy_helper
 from onnxruntime import InferenceSession, SessionOptions, get_available_providers
 
@@ -188,6 +189,15 @@ class IAIOnnxRuntimeModel(RawModel):
         # return self.io_binding.copy_outputs_to_cpu()
         return self.session.run(None, inputs)
 
+    # compatability with RawModel ABC
+    def to(
+        self,
+        device: Optional[torch.device] = None,
+        dtype: Optional[torch.dtype] = None,
+        non_blocking: bool = False,
+    ) -> None:
+        pass
+
     # compatability with diffusers load code
     @classmethod
     def from_pretrained(