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

Remove unused param from ModelCache.

Browse Source
This commit is contained in:
Ryan Dick 2024-08-27 14:36:23 +00:00
parent 5284a870b0
commit 5fefb3b0f4
1 changed files with 0 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
invokeai/backend/model_manager/load/model_cache/model_cache_default.py
View File

@ -54,7 +54,6 @@ class ModelCache(ModelCacheBase[AnyModel]):
max_vram_cache_size: float, max_vram_cache_size: float,
execution_device: torch.device = torch.device("cuda"), execution_device: torch.device = torch.device("cuda"),
storage_device: torch.device = torch.device("cpu"), storage_device: torch.device = torch.device("cpu"),
precision: torch.dtype = torch.float16,
lazy_offloading: bool = True, lazy_offloading: bool = True,
log_memory_usage: bool = False, log_memory_usage: bool = False,
logger: Optional[Logger] = None, logger: Optional[Logger] = None,
@ -65,7 +64,6 @@ class ModelCache(ModelCacheBase[AnyModel]):
:param max_cache_size: Maximum size of the RAM cache [6.0 GB] :param max_cache_size: Maximum size of the RAM cache [6.0 GB]
:param execution_device: Torch device to load active model into [torch.device('cuda')] :param execution_device: Torch device to load active model into [torch.device('cuda')]
:param storage_device: Torch device to save inactive model in [torch.device('cpu')] :param storage_device: Torch device to save inactive model in [torch.device('cpu')]
:param precision: Precision for loaded models [torch.float16]
:param lazy_offloading: Keep model in VRAM until another model needs to be loaded :param lazy_offloading: Keep model in VRAM until another model needs to be loaded
:param log_memory_usage: If True, a memory snapshot will be captured before and after every model cache :param log_memory_usage: If True, a memory snapshot will be captured before and after every model cache
operation, and the result will be logged (at debug level). There is a time cost to capturing the memory operation, and the result will be logged (at debug level). There is a time cost to capturing the memory
@ -74,7 +72,6 @@ class ModelCache(ModelCacheBase[AnyModel]):
""" """
# allow lazy offloading only when vram cache enabled # allow lazy offloading only when vram cache enabled
self._lazy_offloading = lazy_offloading and max_vram_cache_size > 0 self._lazy_offloading = lazy_offloading and max_vram_cache_size > 0
self._precision: torch.dtype = precision
self._max_cache_size: float = max_cache_size self._max_cache_size: float = max_cache_size
self._max_vram_cache_size: float = max_vram_cache_size self._max_vram_cache_size: float = max_vram_cache_size
self._execution_device: torch.device = execution_device self._execution_device: torch.device = execution_device
@ -342,8 +339,6 @@ class ModelCache(ModelCacheBase[AnyModel]):
def make_room(self, size: int) -> None: def make_room(self, size: int) -> None:
"""Make enough room in the cache to accommodate a new model of indicated size.""" """Make enough room in the cache to accommodate a new model of indicated size."""
# calculate how much memory this model will require
# multiplier = 2 if self.precision==torch.float32 else 1
bytes_needed = size bytes_needed = size
maximum_size = self.max_cache_size * GIG # stored in GB, convert to bytes maximum_size = self.max_cache_size * GIG # stored in GB, convert to bytes
current_size = self.cache_size() current_size = self.cache_size()