-
Notifications
You must be signed in to change notification settings - Fork 7
Create a tensor de-duplication pass #66
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
Comments
Hi! I'd love to work on this as a first-time contributor. Could you please assign it to me? |
Please feel free to create a PR. You can create the file in https://github.com/onnx/ir-py/tree/main/src/onnx_ir/passes/common |
Sure, will do so. Thank you:) |
Hi @justinchuby, Thank you for creating this as a first-time contributor issue. I’ve submitted a PR here: #67 implementing the deduplication pass. The logic aligns with the IR’s fingerprinting approach using (tobytes, dtype, shape) and updates graph nodes using Looking forward to any feedback or suggestions you might have! Best regards, |
Signed-off-by: Abhishek Herbert Samuel <[email protected]>
Pass to deduplicate initializers (model weights)
The text was updated successfully, but these errors were encountered: