- Replace global safetensor_allocation_store/safetensor_settings_store and create_safetensor_model_hash
with a per-model annotation (_distorch_v2_meta) stored directly on the inner model object.
- Update distorch_2 to remove global stores and hash creation; parse and consume allocation strings
from inner_model._distorch_v2_meta during model registration and loading.
- Update wrappers, checkpoint_multigpu, device_utils, and __init__ to set and read the new metadata
instead of writing/reading global stores.
- Simplify detection of DisTorch-managed models (check inner_model._distorch_v2_meta) and adjust
logging to surface inner model ids and allocation info.
- Clean up related imports and dead code paths.
Files changed: distorch_2.py, wrappers.py, checkpoint_multigpu.py, device_utils.py, model_management_mgpu.py, __init__.py
- Implemented WanVideoVACEEncode class for encoding with VACE, including input parameters for width, height, number of frames, and strength.
- Enhanced WanVideoEncode class to support multi-GPU encoding, with additional parameters for noise augmentation and latent strength.
- Updated device management to ensure proper device context during encoding processes.
So this is a change from something just newly-released in 2.5.0, but most should either see an improvement or no change to behavior. This was the weakest, and jankiest part of 2.5.0 and my decision to manage a CPU memory leak turned into a too-aggressive solution with unwanted side effects.
This solution should provide a better way to manage `compute` VRAM as the most asked-for feature is a way to remove everything else from VRAM prior to main UNet inference, which this accomplishes nicely, as well as reporting back accurate information DisTorch2 on-device shard sizes.
Refactor memory management in distorch_2.py to patch load_models_gpu instead of LoadedModel.model_memory_required. Implement correct memory reporting based on model flags (eject_models and is_distorch_model), ensuring proper eviction logic and improved handling of virtual VRAM. This drives behavior purely by either comfy core matching or DisTorch flag, fixing potential issues in multi-GPU setups.
John Pollock