WebML WG Teleconference – 16 November 2023 - 15:00-16:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-11-16-wg-agenda.md


WebML WG Teleconference – 16 November 2023 - 15:00-16:00 UTC<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-11-16-wg-agenda.md#webml-wg-teleconference--16-november-2023---1500-1600-utc>
See the timezone table ...
San Francisco (U.S.A. - California)     Thu, 16 November 2023   07:00   UTC-8 hours
Boston (U.S.A. - Massachusetts) Thu, 16 November 2023   10:00   UTC-5 hours
London (United Kingdom - England)       Thu, 16 November 2023   15:00   UTC+0 hours (adjusted for DST)
Berlin (Germany)        Thu, 16 November 2023   16:00   UTC+1 hours (adjusted for DST)
Helsinki (Finland)      Thu, 16 November 2023   17:00   UTC+2 hours (adjusted for DST)
Shanghai (China)        Thu, 16 November 2023   23:00   UTC+8 hours (adjusted for DST)
Tokyo (Japan)   Fri, 17 November 2023   00:00   UTC+9 hours (adjusted for DST)
Corresponding UTC (GMT) Thu, 16 November 2023   15:00 UTC

Other locations: https://www.timeanddate.com/worldclock/fixedtime.html?iso=20231116T15


Logistics<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-11-16-wg-agenda.md#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/2023/11/16-webmachinelearning-minutes.html


Agenda<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-11-16-wg-agenda.md#agenda>
Announcements<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-11-16-wg-agenda.md#announcements>

  *   W3C Web & Network Interest Group rechartering, coordination opportunity with WebML WG

ℹ️ WebNN v2: Review transformer ops spec contributions (continued)<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-11-16-wg-agenda.md#%E2%84%B9%EF%B8%8F-webnn-v2-review-transformer-ops-spec-contributions-continued>

Discuss and review any spec PRs or contributions for the proposed transformer ops informed by the op breakdown exercise.

References:

  *   Op breakdown (w/ TOSA, StableHLO mapping): https://docs.google.com/spreadsheets/d/1ELfHuv2UqP2LoXWLgqsC0L8T_qqfBx48KxzFighl8d8/edit#gid=86906292

  *   Feedback via webmachinelearning/webnn#375<https://github.com/webmachinelearning/webnn/issues/375>

ℹ️ Enhancements<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-11-16-wg-agenda.md#%E2%84%B9%EF%B8%8F-enhancements>

  *   Simplify matmul op

     *    issue: webmachinelearning/webnn#470<https://github.com/webmachinelearning/webnn/issues/470>
  *   Define the algorithm of calculating the effective padding for "same-upper" and "same-lower" option

     *    issue: webmachinelearning/webnn#326<https://github.com/webmachinelearning/webnn/issues/326>
  *   API lacks handling for async ML device errors on the context

     *    issue: webmachinelearning/webnn#477<https://github.com/webmachinelearning/webnn/issues/477>
  *   Remove builder.constant(value, dataType) variant

     *    issue: webmachinelearning/webnn#475<https://github.com/webmachinelearning/webnn/issues/475>
  *   Need to restrict the value of alpha to be positive for elu operation

     *    issue: webmachinelearning/webnn#383<https://github.com/webmachinelearning/webnn/issues/383>
  *   Allow 0 size dimensions

     *    issue: webmachinelearning/webnn#391<https://github.com/webmachinelearning/webnn/issues/391>