Add missing ops for ResNet-50#16
Merged
theHamsta merged 6 commits intoMay 22, 2026
Merged
Conversation
mklimenko-nv
marked this pull request as ready for review
May 20, 2026 08:29
3 tasks
mtavenrath
added a commit
to rustnn/rustnn
that referenced
this pull request
Jun 23, 2026
Run an E2E model via rustnn. Currently depends on rustnn/webnn-graph#16 for the ONNX model conversion to be merged. After fixes related to marking all the nodes as outputs, perfomance of rustnn with TensorRT-RTX backend is similar to native execution. To be added: - [x] Full E2E run from ONNX - [x] Performance comparison against TensorRT-RTX - [ ] FP16 execution Co-authored-by: Markus Tavenrath <mtavenrath@users.noreply.github.com>
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Currently, webnn-graph is mostly focused on LLMs, leaving a gap in convolutional neural networks and diffusion models.
This PR is a first step to close this gap by adding the missing op support:
Expands the sanitize logic for digit-leading ONNX names ("495" -> "_495").
Added a ResNet-50 conversion test that downloads the model from the ONNX model zoo, converts it and checks for the operations count to match. It also caches the model for subsequent local and CI runs.