Disable dynamic_vram when using torch compiler (#12612)

* mp: attach re-construction arguments to model patcher

When making a model-patcher from a unet or ckpt, attach a callable
function that can be called to replay the model construction. This
can be used to deep clone model patcher WRT the actual model.

Originally written by Kosinkadink
f4b99bc623

* mp: Add disable_dynamic clone argument

Add a clone argument that lets a caller clone a ModelPatcher but disable
dynamic to demote the clone to regular MP. This is useful for legacy
features where dynamic_vram support is missing or TBD.

* torch_compile: disable dynamic_vram

This is a bigger feature. Disable for the interim to preserve
functionality.

comfy_extras/nodes_torch_compile.py

@@ -25,7 +25,7 @@ class TorchCompileModel(io.ComfyNode):
 
     @classmethod
     def execute(cls, model, backend) -> io.NodeOutput:
-        m = model.clone()
+        m = model.clone(disable_dynamic=True)
         set_torch_compile_wrapper(model=m, backend=backend, options={"guard_filter_fn": skip_torch_compile_dict})
         return io.NodeOutput(m)