Skip to content

cherry pick 3660 to release/2.8 #3661

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 2 commits into from
Jul 10, 2025
Merged

cherry pick 3660 to release/2.8 #3661

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b27d051
fix compiler cl not found error in windows
lanluo-nvidia Jul 7, 2025
b45223a
constant folding
lanluo-nvidia Jul 10, 2025
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
2 changes: 1 addition & 1 deletion .github/workflows/build-test-windows.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -230,7 +230,7 @@ jobs:
cd dynamo
python -m pytest -ra -n 10 --junitxml=${RUNNER_TEST_RESULTS_DIR}/torch_compile_be_test_results.xml backend/
python -m pytest -ra -n 4 --junitxml=${RUNNER_TEST_RESULTS_DIR}/torch_complete_be_e2e_test_results.xml --ir torch_compile models/test_models.py
python -m pytest -ra --junitxml=${RUNNER_TEST_RESULTS_DIR}/torch_compile_dyn_models_export.xml --ir torch_compile models/test_dyn_models.py
../../../packaging/vc_env_helper.bat python -m pytest -ra --junitxml=${RUNNER_TEST_RESULTS_DIR}/torch_compile_dyn_models_export.xml --ir torch_compile models/test_dyn_models.py
popd

tests-py-dynamo-core:
Expand Down
6 changes: 5 additions & 1 deletion py/torch_tensorrt/dynamo/lowering/passes/constant_folding.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,10 +103,14 @@ def __init__(self, *args: Any, **kwargs: Any) -> None:
self.quantization_ops: Set[torch._ops.OpOverload] = set()
try:
# modelopt import ensures torch.ops.tensorrt.quantize_op.default is registered
import modelopt.torch.quantization as mtq
import modelopt.torch.quantization as mtq # noqa: F401

assert torch.ops.tensorrt.quantize_op.default
assert torch.ops.tensorrt.dynamic_block_quantize_op.default
self.quantization_ops.add(torch.ops.tensorrt.quantize_op.default)
self.quantization_ops.add(
torch.ops.tensorrt.dynamic_block_quantize_op.default
)
except Exception as e:
pass

Expand Down
Loading