WebML WG Teleconference – 2 November 2023 - 14:00-15:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-11-02-wg-agenda.md


WebML WG Teleconference – 2 November 2023 - 14:00-15:00 UTC<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-11-02-wg-agenda.md#webml-wg-teleconference--2-november-2023---1400-1500-utc>
See the timezone table ...
Logistics<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-11-02-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/2023/11/02-webmachinelearning-minutes.html


Agenda<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-11-02-wg-agenda.md#agenda>
ℹ️ WebNN v2: Review transformer ops spec contributions (continued)<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-11-02-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/2023-11-02-wg-agenda.md#%E2%84%B9%EF%B8%8F-enhancements>

  *   Softmax axis absent
     *    issue: webmachinelearning/webnn#466<https://github.com/webmachinelearning/webnn/issues/466>
  *   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>
  *   Simplify matmul op
     *    issue: webmachinelearning/webnn#470<https://github.com/webmachinelearning/webnn/issues/470>