Skip to content

Update custom file name patterns when copy files and remove problematic parameters in export #520

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

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Update custom file name patterns when copy files and remove problematic parameters in export #520

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
7d91e62
update custom file name patterns when copy files in export
Edwardf0t1 Nov 6, 2025
469d913
remove problematic parameters in export
Edwardf0t1 Nov 6, 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
4 changes: 2 additions & 2 deletions examples/llm_ptq/example_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -526,10 +526,10 @@ def copy_custom_model_files(source_path: str, export_path: str, trust_remote_cod
# Common patterns for custom model files that need to be copied
custom_file_patterns = [
"configuration_*.py",
"modeling_*.py",
"modeling*.py",
"tokenization_*.py",
"processing_*.py",
"image_processing_*.py",
"image_processing*.py",
"feature_extraction_*.py",
"*.json",
]
Expand Down
5 changes: 5 additions & 0 deletions modelopt/torch/export/quant_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -849,6 +849,11 @@ def postprocess_state_dict(state_dict: dict, maxbound: float, quantization: str
post_state_dict = {}

for key, value in state_dict.items():
# Skip problematic parameters for specific model architectures, e.g., Nemotron Nano VL models
if key == "vision_model.radio_model.summary_idxs":
logger.info(f"Removing problematic parameter: {key}")
continue

# Skip keys not related to quantizers
if (
"output_quantizer" not in key
Expand Down