Austin Huang

This looks pretty good. @jan-wassenberg if this looks alright to you we can probably go ahead and merge.

This seems interesting and quite doable. I'll need to have a closer look at the paper and revisit tomorrow. On the tactical side, we'll want to tidy up the APIs...

If someone wants to take a stab at this as a flag, happy to have a look at the PR / provide suggestions (add yourself as the assignee for this...

There are some issues with multiturn continuations that are being worked on but not resolved, so I made the default for it to be off for now. Turning it off...

Closing for now, but if anyone prefers the default reverted please chime in here.

With the recent MQA change there was a window when artifact wasn’t in sync (using the kaggle client api code worked but the artifact download didn’t). https://discord.com/channels/1212851822813904947/1212851825334550548/1225712866934521887 might try downloading...

I'm interested in participating as well. One thing that's not clear to me is what level of abstraction wasi-nn is intended to be at? EDIT: I see there's some links...

@abrown thank you for the invitation! I think my questions about the level of abstraction are partially answered here: https://github.com/webmachinelearning/webnn/blob/master/explainer.md#stay-the-course-and-build-machine-learning-solutions-on-webglwebgpu and https://github.com/webmachinelearning/model-loader/blob/master/explainer.md I'm new to this effort but my initial...

@mingqiusun thanks for being so open to input. My personal perspective is that hardware acceleration access is much more valuable a narrow common-denominator inference-only specification. There's a lot that goes...