mirrors/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-09-10 11:35:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

Enable Convolution AutoTuning (#9301)

Browse Source
This commit is contained in:
contentis
2025-09-02 02:33:50 +02:00
committed by GitHub
parent 27e067ce50
commit e2d1e5dad9
2 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
comfy/cli_args.py
View File

@@ -143,6 +143,7 @@ class PerformanceFeature(enum.Enum):
Fp16Accumulation = "fp16_accumulation"
Fp8MatrixMultiplication = "fp8_matrix_mult"
CublasOps = "cublas_ops"
AutoTune = "autotune"
parser.add_argument("--fast", nargs="*", type=PerformanceFeature, help="Enable some untested and potentially quality deteriorating optimizations. --fast with no arguments enables everything. You can pass a list specific optimizations if you only want to enable specific ones. Current valid optimizations: fp16_accumulation fp8_matrix_mult cublas_ops")

3
comfy/ops.py
View File

@@ -52,6 +52,9 @@ except (ModuleNotFoundError, TypeError):
cast_to = comfy.model_management.cast_to #TODO: remove once no more references
if torch.cuda.is_available() and torch.backends.cudnn.is_available() and PerformanceFeature.AutoTune in args.fast:
torch.backends.cudnn.benchmark = True
def cast_to_input(weight, input, non_blocking=False, copy=True):
return comfy.model_management.cast_to(weight, input.dtype, input.device, non_blocking=non_blocking, copy=copy)