WebML WG Teleconference – 12 January 2023 - 15:00-16:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-01-12-wg-agenda.md


WebML WG Teleconference – 12 January 2023 - 15:00-16:00 UTC
San Francisco (U.S.A. - California)     Thu, 12 January 2023    07:00   UTC-8 hours
Boston (U.S.A. - Massachusetts) Thu, 12 January 2023    10:00   UTC-5 hours
London (United Kingdom - England)       Thu, 12 January 2023    15:00   UTC+0 hours (adjusted for DST)
Berlin (Germany)        Thu, 12 January 2023    16:00   UTC+1 hours (adjusted for DST)
Helsinki (Finland)      Thu, 12 January 2023    17:00   UTC+2 hours (adjusted for DST)
Shanghai (China)        Thu, 12 January 2023    23:00   UTC+8 hours (adjusted for DST)
Tokyo (Japan)   Fri, 13 January 2023    00:00   UTC+9 hours (adjusted for DST)
Corresponding UTC (GMT) Thu, 12 January 2023    15:00 UTC

Other locations: https://www.timeanddate.com/worldclock/fixedtime.html?iso=20230112T15


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-01-12-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/2020Apr/0000.html

  *   Minutes: https://www.w3.org/2023/01/12-webmachinelearning-minutes.html


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-01-12-wg-agenda.md#agenda>Agenda
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-01-12-wg-agenda.md#%E2%84%B9%EF%B8%8F-webnn-api-open-prs-and-issues>ℹ️ WebNN API open PRs and issues
Review open PRs and discuss issues. Identify and fast track any priority changes that should get into the initial CR release train.

  *   Add lstm and lstmCell ops, rename MLOperator to MLActivation

     *    PR: webmachinelearning/webnn#321<https://github.com/webmachinelearning/webnn/pull/321>
  *   Simplify MLContext creation: remove MLDeviceType, remove "high-performance" from MLPowerPreference

     *    PR: webmachinelearning/webnn#322<https://github.com/webmachinelearning/webnn/pull/322>
  *   Transfer the input and output views for asynchronous execution

     *    issue: webmachinelearning/webnn#318<https://github.com/webmachinelearning/webnn/issues/318>
     *    PR: webmachinelearning/webnn#323<https://github.com/webmachinelearning/webnn/pull/323>
  *   Improve graph execution steps

     *    issue: webmachinelearning/webnn#316<https://github.com/webmachinelearning/webnn/issues/316>
     *    PR: webmachinelearning/webnn#319<https://github.com/webmachinelearning/webnn/pull/319>
  *   Simplify the operand layout support of conv2d and pooling 2d operations

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-01-12-wg-agenda.md#%E2%84%B9%EF%B8%8F-webnn-api-candidate-recommendation-readiness>ℹ️ WebNN API Candidate Recommendation readiness
Confirm our CR readiness and discuss CR progressive enhancement. Work out a plan for our initial CR publication.

  *   Current CR issues https://github.com/webmachinelearning/webnn/labels/cr


  *   Web platform tests

     *    tracker issue: webmachinelearning/webnn#265<https://github.com/webmachinelearning/webnn/issues/265>
     *   Open webnn-baseline PRs: https://github.com/webmachinelearning/webnn-baseline/pulls

     *   Open wpt PRs: https://github.com/web-platform-tests/wpt/labels/wg-s_webmachinelearning

     *   ➡️ Status: Discuss & resolve any blockers for webnn-baseline and WPT PRs
  *   Use modern WebIDL and Infra standard conventions

     *    tracker issue: webmachinelearning/webnn#210<https://github.com/webmachinelearning/webnn/issues/210>
     *   ➡️ Status: Continue editorial work required to add algorithmic method steps, add internal slots, use getters, setters, define methods and constructors using the modern WebIDL conventions. Focus is on editorial enhancements. Normative changes and new feature work is deferred for later.