WebML WG Teleconference – 27 March 2025 - 15:00-16:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-03-27-wg-agenda.md


WebML WG Teleconference – 27 March 2025 - 15:00-16:00 UTC

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-03-27-wg-agenda.md#webml-wg-teleconference--27-march-2025---1500-1600-utc>

 Important

This meeting takes place one hour later than usual in the US due to Daylight Saving Time<https://www.timeanddate.com/time/dst/2025a.html>.


See the timezone table ...
San Francisco   Thu, 27 March 2025      08:00 adjusted for DST
Boston  Thu, 27 March 2025      11:00 adjusted for DST
London  Thu, 27 March 2025      15:00
Berlin  Thu, 27 March 2025      16:00
Helsinki        Thu, 27 March 2025      17:00
Shanghai        Thu, 27 March 2025      23:00
Tokyo   Fri, 28 March 2025      00:00
UTC     Thu, 27 March 2025      15:00 UTC


Other locations: https://www.timeanddate.com/worldclock/fixedtime.html?iso=20250327T15


Logistics
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-03-27-wg-agenda.md#logistics>


  *   Chair: Anssi
  *   Scribe: 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/2025/03/27-webmachinelearning-minutes.html


Agenda
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-03-27-wg-agenda.md#agenda>

🧪 Incubations summary
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-03-27-wg-agenda.md#-incubations-summary>


A summary of the most recent WebML Community Group meeting will be shared to keep the Working Group abreast of incubations.

ℹ️ WebNN wide review update
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-03-27-wg-agenda.md#%E2%84%B9%EF%B8%8F-webnn-wide-review-update>


A new round of review requests are now in flight:

  *   ♿ Accessibility w3c/a11y-request#105<https://github.com/w3c/a11y-request/issues/105>
  *   📐 Architecture w3ctag/design-reviews#1072<https://github.com/w3ctag/design-reviews/issues/1072>
  *   🌍 Internationalisation w3c/i18n-request#258<https://github.com/w3c/i18n-request/issues/258>
  *   🔍 Privacy w3cping/privacy-request#156<https://github.com/w3cping/privacy-request/issues/156>
  *   🔒 Security w3c/security-request#85<https://github.com/w3c/security-request/issues/85>


Discuss the requests, expectations, fine-tune as needed. Wide review tracker for discussion:

  *   ⨀ webmachinelearning/webnn#239<https://github.com/webmachinelearning/webnn/issues/239>

ℹ️ Query mechanism for supported devices
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-03-27-wg-agenda.md#%E2%84%B9%EF%B8%8F-query-mechanism-for-supported-devices>


Discuss new use case feedback received. Address questions on the capacity concept.

  *   ⨀ webmachinelearning/webnn#815<https://github.com/webmachinelearning/webnn/issues/815>

ℹ️ Caching mechanism for MLGraph
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-03-27-wg-agenda.md#%E2%84%B9%EF%B8%8F-caching-mechanism-for-mlgraph>


Gauge interest to initiate work on an explainer, prototyping intent, identify any blockers.

  *   ⨀ webmachinelearning/webnn#807<https://github.com/webmachinelearning/webnn/issues/807>


 Note

We will also discuss the following issues as appropriate, time allowing.

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

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-03-27-wg-agenda.md#%EF%B8%8F-feature-request-issues>

  *   Remove pool2d MLRoundingType
     *   ⨀ webmachinelearning/webnn#324<https://github.com/webmachinelearning/webnn/issues/324>
     *   ⨀ closes also webmachinelearning/webnn#374<https://github.com/webmachinelearning/webnn/issues/374>
     *   ⛙ webmachinelearning/webnn#770<https://github.com/webmachinelearning/webnn/pull/770>
     *   ☰ Address remaining PR review comments.

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

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-03-27-wg-agenda.md#%EF%B8%8F-interop-issues>

  *   Behavior when there are NaNs in argmin/max inputs

     *   ⨀ webmachinelearning/webnn#811<https://github.com/webmachinelearning/webnn/issues/811>
     *   ☰ Discuss how backends handle NaNs in the input and agree on next steps.
  *   (de)quantization behaviors on Core ML

     *   ⨀ webmachinelearning/webnn#822<https://github.com/webmachinelearning/webnn/issues/822>
     *   ☰ Discuss quantize/dequantize Core ML implementation feedback

⭐ [new] issues

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-03-27-wg-agenda.md#-new-issues>

Topics that warrant dedicated issues for further discussion:

  *   dequantizeLinear emulation improvement by expand augmentation:

     *   ⨀ webmachinelearning/webnn#779 (comment)<https://github.com/webmachinelearning/webnn/issues/779#issuecomment-2689214272>
  *   Gather multiaxis operator proposal to more generically express a gathering operation:

     *   ⨀ webmachinelearning/webnn#767 (comment)<https://github.com/webmachinelearning/webnn/issues/767#issuecomment-2688528116>
     *   ☰ Multigather.md<https://github.com/fdwr/MachineLearningOperators/blob/master/Multigather.md>