InvokeAI/invokeai/backend
Lincoln Stein e93f4d632d
[util] Add generic torch device class (#6174)
* introduce new abstraction layer for GPU devices

* add unit test for device abstraction

* fix ruff

* convert TorchDeviceSelect into a stateless class

* move logic to select context-specific execution device into context API

* add mock hardware environments to pytest

* remove dangling mocker fixture

* fix unit test for running on non-CUDA systems

* remove unimplemented get_execution_device() call

* remove autocast precision

* Multiple changes:

1. Remove TorchDeviceSelect.get_execution_device(), as well as calls to
   context.models.get_execution_device().
2. Rename TorchDeviceSelect to TorchDevice
3. Added back the legacy public API defined in `invocation_api`, including
   choose_precision().
4. Added a config file migration script to accommodate removal of precision=autocast.

* add deprecation warnings to choose_torch_device() and choose_precision()

* fix test crash

* remove app_config argument from choose_torch_device() and choose_torch_dtype()

---------

Co-authored-by: Lincoln Stein <lstein@gmail.com>
2024-04-15 13:12:49 +00:00
..
image_util [util] Add generic torch device class (#6174) 2024-04-15 13:12:49 +00:00
ip_adapter Create a UNetAttentionPatcher for patching UNet models with CustomAttnProcessor2_0 modules. 2024-04-09 08:12:12 -04:00
model_hash feat(mm): rename "blake3" to "blake3_multi" 2024-03-22 08:26:36 +11:00
model_manager [util] Add generic torch device class (#6174) 2024-04-15 13:12:49 +00:00
onnx final tidying before marking PR as ready for review 2024-03-01 10:42:33 +11:00
stable_diffusion [util] Add generic torch device class (#6174) 2024-04-15 13:12:49 +00:00
tiles feat(nodes): extract LATENT_SCALE_FACTOR to constants.py 2024-03-01 10:42:33 +11:00
util [util] Add generic torch device class (#6174) 2024-04-15 13:12:49 +00:00
__init__.py consolidate model manager parts into a single class 2024-03-01 10:42:33 +11:00
lora.py final tidying before marking PR as ready for review 2024-03-01 10:42:33 +11:00
model_patcher.py chore: ruff 2024-03-01 10:42:33 +11:00
raw_model.py final tidying before marking PR as ready for review 2024-03-01 10:42:33 +11:00
textual_inversion.py final tidying before marking PR as ready for review 2024-03-01 10:42:33 +11:00