Skip to content

fix:vit_attention ut #48884

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Dec 9, 2022
Merged

fix:vit_attention ut #48884

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 10 additions & 1 deletion python/paddle/fluid/tests/unittests/ir/inference/test_trt_convert_multihead_matmul.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1074,7 +1074,16 @@ def generate_trt_nodes_num():
)

def add_skip_trt_case(self):
pass
def teller1(program_config, predictor_config):
if self.trt_param.precision == paddle_infer.PrecisionType.Half:
return True
return False

self.add_skip_case(
teller1,
SkipReasons.TRT_NOT_IMPLEMENTED,
"The output has diff between gpu and trt in fp16 mode.",
)

def test(self):
self.add_skip_trt_case()
Expand Down