WebML WG Teleconference – 30 January 2025 - 15:00-16:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-01-30-wg-agenda.md


WebML WG Teleconference – 30 January 2025 - 15:00-16:00 UTC
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-01-30-wg-agenda.md#webml-wg-teleconference--30-january-2025---1500-1600-utc>
See the timezone table ...

Logistics

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-01-30-wg-agenda.md#logistics>

  *   Chair: Anssi
  *   IRC: irc://irc.w3.org:6667/#webmachinelearning

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

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

  *   Minutes: https://www.w3.org/2025/01/30-webmachinelearning-minutes.html


Agenda
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-01-30-wg-agenda.md#agenda>

ℹ️ Device selection
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-01-30-wg-agenda.md#%E2%84%B9%EF%B8%8F-device-selection>


Review spec PR for the Proposed Minimum Viable Solution outlined in the explainer and/or discuss open questions.

  *   ☰ device-selection-explainer.md<https://github.com/webmachinelearning/webnn/blob/main/device-selection-explainer.md>
  *   ⛙ Spec PR (subject to availability)

ℹ️ Operator set Wave 3
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-01-30-wg-agenda.md#%E2%84%B9%EF%B8%8F-operator-set-wave-3>


Review draft PR and (many!) issues it closes.


PR also welcomes contributions to remaining algorithm steps and examples to the scattering/gathering operators.


  *   ⨀ webmachinelearning/webnn#375<https://github.com/webmachinelearning/webnn/issues/375>
  *   ⛙ webmachinelearning/webnn#805<https://github.com/webmachinelearning/webnn/pull/805>


Closes: ⨀ #93<https://github.com/webmachinelearning/webnn/issues/93>, ⨀ #467<https://github.com/webmachinelearning/webnn/issues/467>, ⨀ #772<https://github.com/webmachinelearning/webnn/issues/772>, ⨀ #767<https://github.com/webmachinelearning/webnn/issues/767>, ⨀ #773<https://github.com/webmachinelearning/webnn/issues/773>, ⨀ #779<https://github.com/webmachinelearning/webnn/issues/779>

🏷️ operator specific<https://github.com/webmachinelearning/webnn/labels/operator%20specific> issues

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-01-30-wg-agenda.md#%EF%B8%8F-operator-specific-issues>

  *   Disallow operations on scalar tensors that are no-ops
     *   ⨀ webmachinelearning/webnn#794<https://github.com/webmachinelearning/webnn/issues/794>
     *   ☰ Review scalar support by operator, discuss whether 0D to 1D reshape path is viable.

🏷️ feature request<https://github.com/webmachinelearning/webnn/labels/feature%20request> issues

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-01-30-wg-agenda.md#%EF%B8%8F-feature-request-issues>

  *   Caching mechanism for MLGraph

     *   ⨀ webmachinelearning/webnn#807<https://github.com/webmachinelearning/webnn/issues/807>
     *   ☰ Discuss caching mechanism for MLGraph, WebGPU shader caching, Storage APIs, assess the privacy impact.
  *   Expose WebNN API to service workers

     *   ⨀ webmachinelearning/webnn#804<https://github.com/webmachinelearning/webnn/issues/804>
     *   ⨀ related gpuweb/gpuweb#4197<https://github.com/gpuweb/gpuweb/issues/4197>
     *   ☰ Discuss and identify use cases (extensions, others?), implementation considerations.
  *   Remove pool2d MLRoundingType

     *   ⨀ webmachinelearning/webnn#324<https://github.com/webmachinelearning/webnn/issues/324>
     *   ⛙ webmachinelearning/webnn#770<https://github.com/webmachinelearning/webnn/pull/770>
     *   ☰ Discuss remaining PR review comments.

🏷️ bug<https://github.com/webmachinelearning/webnn/labels/bug> issues

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-01-30-wg-agenda.md#%EF%B8%8F-bug-issues>

  *   Reject promises for in-progress operations on an MLTensor if it is destroyed

     *   ⨀ follow-up to webmachinelearning/webnn#477<https://github.com/webmachinelearning/webnn/issues/477>
     *   ⛙ webmachinelearning/webnn#799<https://github.com/webmachinelearning/webnn/pull/799>
     *   ☰ Review the PR that update the spec to match the Chromium implementation.

ℹ️ Community Group meeting scheduling poll
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-01-30-wg-agenda.md#%E2%84%B9%EF%B8%8F-community-group-meeting-scheduling-poll>


If you’re interested in Community Group incubations, please respond to the meeting scheduling poll by EOB 29 Jan 2025:


  *   ⏱️ https://doodle.com/meeting/participate/id/e5VrnyAa



More information:


  *   ☰ Announcement https://lists.w3.org/Archives/Public/public-webmachinelearning/2025Jan/0000.html

  *   🧪 Incubations https://webmachinelearning.github.io/incubations/