RESCHEDULED to WebML WG Teleconference – 29 June 2023 - 14:00-15:00 UTC

I rescheduled this meeting to June 29, 2023 to avoid overlap with the Dragon Boat Festival, a traditional Chinese holiday observed in 22 June this year.

See the updated agenda below with the new date.

To be on the safe side, please delete the old 22 June meeting from your calendar before accepting the update one I just sent. I know some calendaring systems fail to update otherwise.

To those whom it concerns, please enjoy Zongzi and the racing dragon boats! 🐉🚣

Thanks,

-Anssi

On 15. Jun 2023, at 13.10, Kostiainen, Anssi <anssi.kostiainen@intel.com<mailto:anssi.kostiainen@intel.com>> wrote:

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-06-22-wg-agenda.md


Note: we’ve updated our Zoom URL starting with this meeting. The invite you have just received also contains this updated information. You’ll also find the new Zoom URL from the W3C Member-only “Joining instructions” link below.


WebML WG Teleconference – 29 June 2023 - 14:00-15:00 UTC
See the timezone table ...
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-06-29-wg-agenda.md#logistics>Logistics

  *   Chair: Anssi
  *   Scribe: ? (see howto<https://github.com/webmachinelearning/meetings/blob/main/scribe-howto.md>, volunteers welcome!)
  *   IRC: irc://irc.w3.org:6667/#webmachinelearning

  *   IRC web client: https://irc.w3.org/?channels=#webmachinelearning

  *   Joining instructions: https://lists.w3.org/Archives/Member/internal-webmachinelearning/2023Jun/0000.html

  *   Minutes: https://www.w3.org/2023/06/29-webmachinelearning-minutes.html


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-06-29-wg-agenda.md#agenda>Agenda
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-06-29-wg-agenda.md#%E2%84%B9%EF%B8%8F-webnn-v2-text-to-image-and-text-to-text-use-cases-and-requirements>ℹ️ WebNN v2: text-to-image and text-to-text use cases and requirements

Discuss transformer-based generative AI use cases for text-to-image and text-to-text models. Solicit input on new ops and data types required to support selected models informed by prototyping efforts. Background material:

  *   Transformer-based models and use cases discussion: webmachinelearning/webnn#375<https://github.com/webmachinelearning/webnn/issues/375>
  *   WebNN DirectML prototype: fdwr/chromium-src-webnn-dml#1<https://github.com/fdwr/chromium-src-webnn-dml/pull/1>
  *   Transformers.js feasible tasks: https://lists.w3.org/Archives/Public/www-archive/2023Jun/att-0000/Transformers_js.pdf


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-06-29-wg-agenda.md#%E2%84%B9%EF%B8%8F-webidl-and-infra-standard-conventions>ℹ️ WebIDL and Infra standard conventions

Per feedback we've shifted to use an integration branch for this conventions alignment task. We'll review the work mode to ensure everyone's up to date.

Task list: webmachinelearning/webnn#210 (comment)<https://github.com/webmachinelearning/webnn/issues/210#issuecomment-1326361748>

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-06-29-wg-agenda.md#%E2%84%B9%EF%B8%8F-new-features>ℹ️ New features

  *   Allow 0 size dimensions
     *    issue: webmachinelearning/webnn#391<https://github.com/webmachinelearning/webnn/issues/391>

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-06-29-wg-agenda.md#%E2%84%B9%EF%B8%8F-enhancements>ℹ️ Enhancements

  *   split() into sizes not widely supported
     *    issue: webmachinelearning/webnn#392<https://github.com/webmachinelearning/webnn/issues/392>
  *   Clarify the restriction for minValue and maxValue of MLClampOptions
     *    issue: webmachinelearning/webnn#396<https://github.com/webmachinelearning/webnn/issues/396>