Comfy Aimdo 0.4.10 + Dynamic --reserve-vram + --vram-headroom (#14480)

* main: implement --vram-headroom

Implement --vram-headroom for dynamic vram as a hybrid debug/diagnostic
option that can be used for people who still report shared VRAM spills.
They can trial and error the setting to maintain a bit more headroom to
avoid shared VRAM spills.

* main: implement --reserve-vram

Implement --reserve-vram as extra headroom on the simple method which
is semantically as close as possible to the stated functionality and
formet behaviour of non-dynamic VRAM.

main.py

@@ -55,7 +55,7 @@ if __name__ == "__main__" and args.debug_hang:
 import comfy_aimdo.control
 
 if enables_dynamic_vram():
-    comfy_aimdo.control.init()
+    comfy_aimdo.control.init(simple_vram_headroom=None if args.reserve_vram is None else int(args.reserve_vram * 1024 ** 3))
 
 if os.name == "nt":
     os.environ['MIMALLOC_PURGE_DELAY'] = '0'
@@ -231,7 +231,7 @@ import comfy.model_patcher
 if args.enable_dynamic_vram or (enables_dynamic_vram() and comfy.model_management.is_nvidia() and not comfy.model_management.is_wsl()):
     if (not args.enable_dynamic_vram) and (comfy.model_management.torch_version_numeric < (2, 8)):
         logging.warning("Unsupported Pytorch detected. DynamicVRAM support requires Pytorch version 2.8 or later. Falling back to legacy ModelPatcher. VRAM estimates may be unreliable especially on Windows")
-    elif comfy_aimdo.control.init_devices(d.index for d in comfy.model_management.get_all_torch_devices()):
+    elif comfy_aimdo.control.init_devices((d.index, int(args.vram_headroom * 1024 ** 3)) for d in comfy.model_management.get_all_torch_devices()):
         if args.verbose == 'DEBUG':
             comfy_aimdo.control.set_log_debug()
         elif args.verbose == 'CRITICAL':