fixes for ort-1.17 #596
Closed
fixes for ort-1.17 #596
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
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
5 tasks
Honry
added a commit
to Honry/transformers.js
that referenced
this pull request
Feb 28, 2024
This is a very rough example to enable WebNN in transfermer.js, I just add some hard codes to make the "Image classification w/ google/vite-base-patch16-224" fp32 model work with ORT Web WebNN EP. This PR depends on huggingface#596
Honry
added a commit
to Honry/transformers.js
that referenced
this pull request
Feb 28, 2024
This is a very rough example to enable WebNN in transformers.js. I just add some hard codes to make the "Image classification w/ google/vite-base-patch16-224" fp32 model work with ORT Web WebNN EP. This PR depends on huggingface#596
|
I think this one is included in the v3 branch - closing. |
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Outdated suggestions cannot be applied.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.
the ort tensor object in 1.17 has changed to add support for keeping webgpu tensors on gpu (ie to avoid copies of kv_cache or hidden state). As result the Object.assign() no longer works.
Either we extend the ort tensor or we decouple by keeping it around in the transformers.js tensor ... we think later is the cleanest.
Take a look and let us know. Using extend is another option that would work.