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

expose max_cache_size in config

Browse Source
This commit is contained in:
Eugene Brodsky 2023-07-04 17:05:35 -04:00
parent 66c10cc2f7
commit 7170e82f73
2 changed files with 28 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
invokeai/app/services/config.py
View File

@ -367,7 +367,8 @@ setting environment variables INVOKEAI_<setting>.
always_use_cpu : bool = Field(default=False, description="If true, use the CPU for rendering even if a GPU is available.", category='Memory/Performance')
free_gpu_mem : bool = Field(default=False, description="If true, purge model from GPU after each generation.", category='Memory/Performance')
max_loaded_models : int = Field(default=3, gt=0, description="Maximum number of models to keep in memory for rapid switching", category='Memory/Performance')
max_loaded_models : int = Field(default=3, gt=0, description="(DEPRECATED: use max_cache_size) Maximum number of models to keep in memory for rapid switching", category='Memory/Performance')
max_cache_size : float = Field(default=6.0, gt=0, description="Maximum memory amount used by model cache for rapid switching", category='Memory/Performance')
precision : Literal[tuple(['auto','float16','float32','autocast'])] = Field(default='float16',description='Floating point precision', category='Memory/Performance')
sequential_guidance : bool = Field(default=False, description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements", category='Memory/Performance')
xformers_enabled : bool = Field(default=True, description="Enable/disable memory-efficient attention", category='Memory/Performance')

2
invokeai/app/services/model_manager_service.py
View File

@ -206,6 +206,8 @@ class ModelManagerService(ModelManagerServiceBase):
if hasattr(config,'max_cache_size') \
else config.max_loaded_models * 2.5
logger.debug(f"Maximum RAM cache size: {max_cache_size} GiB")
sequential_offload = config.sequential_guidance
self.mgr = ModelManager(