You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Adding more aliases for f32 and f16 to make it easier on users
Signed-off-by: Naren Dasan <[email protected]>
Signed-off-by: Naren Dasan <[email protected]>
"(Repeatable) Enabling an operating precision for kernels to use when building the engine (Int8 requires a calibration-cache argument) [ float | float32 | f32 | half | float16 | f16 | int8 | i8 ] (default: float)",
217
+
"(Repeatable) Enabling an operating precision for kernels to use when building the engine (Int8 requires a calibration-cache argument) [ float | float32 | f32 | fp32 | half | float16 | f16 | fp16 | int8 | i8 | char ] (default: float)",
218
218
{'p', "enabled-precison"});
219
219
args::ValueFlag<std::string> device_type(
220
220
parser,
@@ -434,7 +434,7 @@ int main(int argc, char** argv) {
0 commit comments