Support tinygrad inference #3
Draft
Conversation
This file contains 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
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Outdated suggestions cannot be applied.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.
This PR adds support for
tissue_fastbrainchopinference through tinygrad's WebGPU.net.jswhich contains the exported WebGPU kernelsnet.safetensorswhich contains the weights in safetensor formatortinference calls withtinygradcallsI tested with the dist build, had some issues with running the dev build.
To make it a de-factor drop-in replacement, the argmax is not included in the model, but I can move it in very easily.
Also, for now I just commented out the onnx calls, but for the final version I'd like to add a switch to change between onnx vs. tinygrad, plus some perf comparison.
Segmentation looks fine: