Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

[util] Add generic torch device class (#6174)

Browse Source 
* 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>
This commit is contained in:
Lincoln Stein
2024-04-15 09:12:49 -04:00
committed by GitHub
parent 5a8489bbfc
commit e93f4d632d
20 changed files with 327 additions and 176 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
invokeai/backend/model_manager/load/load_default.py
View File

@ -18,7 +18,7 @@ from invokeai.backend.model_manager.load.load_base import LoadedModel, ModelLoad
from invokeai.backend.model_manager.load.model_cache.model_cache_base import ModelCacheBase, ModelLockerBase
from invokeai.backend.model_manager.load.model_util import calc_model_size_by_data, calc_model_size_by_fs
from invokeai.backend.model_manager.load.optimizations import skip_torch_weight_init
from invokeai.backend.util.devices import choose_torch_device, torch_dtype
from invokeai.backend.util.devices import TorchDevice
# TO DO: The loader is not thread safe!
@ -37,7 +37,7 @@ class ModelLoader(ModelLoaderBase):
self._logger = logger
self._ram_cache = ram_cache
self._convert_cache = convert_cache
self._torch_dtype = torch_dtype(choose_torch_device())
self._torch_dtype = TorchDevice.choose_torch_dtype()
def load_model(self, model_config: AnyModelConfig, submodel_type: Optional[SubModelType] = None) -> LoadedModel:
"""