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

14
invokeai/backend/model_manager/load/model_cache/model_cache_default.py
View File

@ -30,15 +30,12 @@ import torch
from invokeai.backend.model_manager import AnyModel, SubModelType
from invokeai.backend.model_manager.load.memory_snapshot import MemorySnapshot, get_pretty_snapshot_diff
from invokeai.backend.util.devices import choose_torch_device
from invokeai.backend.util.devices import TorchDevice
from invokeai.backend.util.logging import InvokeAILogger
from .model_cache_base import CacheRecord, CacheStats, ModelCacheBase, ModelLockerBase
from .model_locker import ModelLocker
if choose_torch_device() == torch.device("mps"):
from torch import mps
# Maximum size of the cache, in gigs
# Default is roughly enough to hold three fp16 diffusers models in RAM simultaneously
DEFAULT_MAX_CACHE_SIZE = 6.0
@ -244,9 +241,7 @@ class ModelCache(ModelCacheBase[AnyModel]):
f"Removing {cache_entry.key} from VRAM to free {(cache_entry.size/GIG):.2f}GB; vram free = {(torch.cuda.memory_allocated()/GIG):.2f}GB"
)
torch.cuda.empty_cache()
if choose_torch_device() == torch.device("mps"):
mps.empty_cache()
TorchDevice.empty_cache()
def move_model_to_device(self, cache_entry: CacheRecord[AnyModel], target_device: torch.device) -> None:
"""Move model into the indicated device.
@ -416,10 +411,7 @@ class ModelCache(ModelCacheBase[AnyModel]):
self.stats.cleared = models_cleared
gc.collect()
torch.cuda.empty_cache()
if choose_torch_device() == torch.device("mps"):
mps.empty_cache()
TorchDevice.empty_cache()
self.logger.debug(f"After making room: cached_models={len(self._cached_models)}")
def _delete_cache_entry(self, cache_entry: CacheRecord[AnyModel]) -> None: