Skip to content

Commit bef9548

Browse files
authored
fix: Change equals-check from reference to value for BERT model not compiling in FX (#1539)
1 parent 063be0d commit bef9548

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

py/torch_tensorrt/fx/converters/acc_ops_converters.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3369,7 +3369,7 @@ def acc_ops_gelu(
33693369
) -> Union[TRTTensor, Sequence[TRTTensor]]:
33703370
input_val = kwargs["input"]
33713371
approximate = kwargs["approximate"]
3372-
if approximate is not "none":
3372+
if approximate != "none":
33733373
raise RuntimeError("GeLU converter currently doesn't support fast gelu compute")
33743374
if not isinstance(input_val, TRTTensor):
33753375
raise RuntimeError(

0 commit comments

Comments
 (0)