Skip to content
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

[Conformance][TorchFX] Run CUDA test only with --cuda argument enabled #3259

Merged
merged 1 commit into from
Feb 6, 2025
Merged

[Conformance][TorchFX] Run CUDA test only with --cuda argument enabled #3259

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
7 changes: 5 additions & 2 deletions tests/post_training/test_quantize_conformance.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -213,8 +213,11 @@ def fixture_wc_report_data(output_dir, run_benchmark_app, pytestconfig):
def maybe_skip_test_case(test_model_param, run_fp32_backend, run_torch_cuda_backend, batch_size):
if test_model_param["backend"] == BackendType.FP32 and not run_fp32_backend:
pytest.skip("To run test for not quantized model use --fp32 argument")
if test_model_param["backend"] == BackendType.CUDA_TORCH and not run_torch_cuda_backend:
pytest.skip("To run test for CUDA_TORCH backend use --cuda argument")
if (
test_model_param["backend"] in [BackendType.CUDA_TORCH, BackendType.CUDA_FX_TORCH]
and not run_torch_cuda_backend
):
pytest.skip(f"To run test for {test_model_param['backend'].value} backend use --cuda argument")
if batch_size and batch_size > 1 and test_model_param.get("batch_size", 1) == 1:
pytest.skip("The model does not support batch_size > 1. Please use --batch-size 1.")
return test_model_param
Expand Down
Loading