feat: revert revert neighbor mask - #316
Open
SakodaShintaro wants to merge 11 commits into
Open
SakodaShintaro wants to merge 11 commits into
SakodaShintaro wants to merge 11 commits into
Conversation
torch2onnx.py compares a CPU (strict FP32) torch reference against an ORT session whose CUDA EP defaults to TF32 matmuls on Ampere+, so the validation diff was dominated by TF32's 10-bit mantissa (~1e-3), not by export correctness. Disable TF32 on both sides for validation only: - pass use_tf32=0 to CUDAExecutionProvider and set NVIDIA_TF32_OVERRIDE=0 in the ORT subprocess - explicitly disable torch TF32 backends flags Deployed sessions keep the (faster) TF32 default.
This reverts commit d500b75.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.