Make Convolution AutoTuning opt-in for now

This commit is contained in:
lspindler 2025-08-22 10:12:23 +02:00
parent ad92e3fa57
commit 771b337e89
2 changed files with 2 additions and 1 deletions

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")

View File

@ -52,7 +52,7 @@ 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():
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):