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.

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

Fix table transformers cuda export #1775

Closed
wants to merge 1 commit into from
Closed
Changes from all commits
Commits
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
3 changes: 1 addition & 2 deletions optimum/exporters/onnx/convert.py
Original file line number Diff line number Diff line change
Expand Up @@ -274,8 +274,7 @@ def _run_validation(

# Create ONNX Runtime session
session_options = SessionOptions()
# We could well set ORT_DISABLE_ALL here, but it makes CUDA export with O4 of gpt_neo fail
Copy link
Contributor Author

@mht-sharma mht-sharma Mar 26, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Little confused by comment, does the export of gpt_neo fails with DISABLE?

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

According to the comment at least

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I tried with EleutherAI/gpt-neo-1.3B and now the gpt-neo export seems to work with the DISABLE_ALL.

session_options.graph_optimization_level = GraphOptimizationLevel.ORT_ENABLE_BASIC
session_options.graph_optimization_level = GraphOptimizationLevel.ORT_DISABLE_ALL

if device.startswith("cuda"):
provider = "CUDAExecutionProvider"
Expand Down
Loading