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

look into ONNX runtime #650

Open
tharvik opened this issue Mar 18, 2024 · 7 comments
Open

look into ONNX runtime #650

tharvik opened this issue Mar 18, 2024 · 7 comments
Assignees
Milestone

Comments

@tharvik
Copy link
Collaborator

tharvik commented Mar 18, 2024

ONNX has a JavaScript API, it seems to be the new framework on the bloc.

currently, we are using TensorFlowJS everywhere. to support more runtime, we would need to first abstract from it.

  • some of our types are typedef of tf's ones: Dataset, Weights
  • aggregation, validator, data_loader, preprocessing are all using tf types
@JulienVig
Copy link
Collaborator

JulienVig commented Mar 18, 2024

@martinjaggi
Copy link
Member

roadmap (not very LLM specific but good)

transformers.js uses it, and would easily give us tokenizers and model converters to/from HF which is crucial

@tharvik tharvik added this to the v4.0.0 milestone Jul 23, 2024
@tharvik tharvik self-assigned this Aug 26, 2024
@bhack
Copy link

bhack commented Aug 27, 2024

https://opensource.microsoft.com/blog/2024/02/06/on-device-training-training-a-model-in-browser/

@tharvik
Copy link
Collaborator Author

tharvik commented Nov 12, 2024

@JulienVig
Copy link
Collaborator

😭

@bhack
Copy link

bhack commented Nov 12, 2024

Probably one way to gain momentum is to push for training in the new W3C forming standards:
https://github.com/webmachinelearning/webnn/blob/main/explainer.md?plain=1#L187

@tharvik
Copy link
Collaborator Author

tharvik commented Dec 2, 2024

per discussion with @martinjaggi and upstream, we can maintain our own fork with training support.

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

No branches or pull requests

4 participants