In #6490 we enabled non-blocking torch device transfers throughout the model manager's memory management code. When using this torch feature, torch attempts to wait until the tensor transfer has completed before allowing any access to the tensor. Theoretically, that should make this a safe feature to use.
This provides a small performance improvement but causes race conditions in some situations. Specific platforms/systems are affected, and complicated data dependencies can make this unsafe.
- Intermittent black images on MPS devices - reported on discord and #6545, fixed with special handling in #6549.
- Intermittent OOMs and black images on a P4000 GPU on Windows - reported in #6613, fixed in this commit.
On my system, I haven't experience any issues with generation, but targeted testing of non-blocking ops did expose a race condition when moving tensors from CUDA to CPU.
One workaround is to use torch streams with manual sync points. Our application logic is complicated enough that this would be a lot of work and feels ripe for edge cases and missed spots.
Much safer is to fully revert non-locking - which is what this change does.
We can get black outputs when moving tensors from CPU to MPS. It appears MPS to CPU is fine. See:
- https://github.com/pytorch/pytorch/issues/107455
- https://discuss.pytorch.org/t/should-we-set-non-blocking-to-true/38234/28
Changes:
- Add properties for each device on `TorchDevice` as a convenience.
- Add `get_non_blocking` static method on `TorchDevice`. This utility takes a torch device and returns the flag to be used for non_blocking when moving a tensor to the device provided.
- Update model patching and caching APIs to use this new utility.
Fixes: #6545
* 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>
* 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 added during penultimate review
---------
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>
- Rename old "model_management" directory to "model_management_OLD" in order to catch
dangling references to original model manager.
- Caught and fixed most dangling references (still checking)
- Rename lora, textual_inversion and model_patcher modules
- Introduce a RawModel base class to simplfy the Union returned by the
model loaders.
- Tidy up the model manager 2-related tests. Add useful fixtures, and
a finalizer to the queue and installer fixtures that will stop the
services and release threads.
