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 FoldConstants tranformation exiting early to redo shape annotations #107

Merged
merged 82 commits into from
Dec 9, 2024

Conversation

iksnagreb
Copy link
Contributor

This fixes some weird behavior where folding multiple nodes at once breaks the graph after the next shape inference. Closes #104

maltanar and others added 27 commits September 12, 2024 10:14
…_commutative_inputs

Add cleanup transformation sorting inputs of commutative operations
…dentity_ops

Fix RemoveIdentityOps not correctly handling ops following fork-nodes
…eature/remove_id_dropout

Remove Dropout with ratio=0 with RemoveIdentityOps
now we have the tests to show that this works fine
…eature/remove_forked_identity

Remove identity nodes with output forking
…eature/fp16_fixes

Fixes for fp16 tensors and datatypes in ONNX
@maltanar
Copy link
Collaborator

maltanar commented Dec 9, 2024

Thank you @iksnagreb - LGTM!

@maltanar maltanar merged commit 9b22db4 into fastmachinelearning:main Dec 9, 2024
5 checks passed
@maltanar maltanar added this to the v0.4.0 milestone Dec 20, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Strage Behavior of FoldConstants Transformation
8 participants