Enable Convolution AutoTuning (#9301)

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

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")