WebML WG Teleconference – 5 June 2025 - 15:00-16:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-05-wg-agenda.md


WebML WG Teleconference – 5 June 2025 - 15:00-16:00 UTC
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-05-wg-agenda.md#webml-wg-teleconference--5-june-2025---1500-1600-utc>
See the timezone table ...
Logistics
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-05-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/2025/06/05-webmachinelearning-minutes.html


Agenda
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-05-wg-agenda.md#agenda>
🧪 Incubations
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-05-wg-agenda.md#-incubations>

Discuss recent WebML Community Group developments to keep the Working Group abreast of incubation progress.

New adopted incubations:

  *   🌱 Proofreader API https://github.com/webmachinelearning/proofreader-api


New implementation experience:

  *   ⚙️ AiBrow https://github.com/axonzeta/aibrow


🏷️ Operator specific issues
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-05-wg-agenda.md#%EF%B8%8F-operator-specific-issues>

Review and discuss operator specific issues that reduce code complexity and improve maintainability, e.g.:

  *   The minimum data type set, web-platform-tests updates

     *   ⨀ webmachinelearning/webnn#853<https://github.com/webmachinelearning/webnn/issues/853>
  *   layerNormalization, Core ML question/clarification

     *   ⨀ webmachinelearning/webnn#748<https://github.com/webmachinelearning/webnn/issues/748>
  *   triangular, consensus to keep the op, close?

     *   ⨀ webmachinelearning/webnn#768<https://github.com/webmachinelearning/webnn/issues/768>

ℹ️ Wide review
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-05-wg-agenda.md#%E2%84%B9%EF%B8%8F-wide-review>

Discuss interim wide review feedback: i18n completed, a11y & Privacy proposals, TAG/Arch and Security WIP.

  *   ☰ webmachinelearning/webnn#239 (comment)<https://github.com/webmachinelearning/webnn/issues/239#issuecomment-2740740891>

ℹ️ Caching mechanism for MLGraph
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-05-wg-agenda.md#%E2%84%B9%EF%B8%8F-caching-mechanism-for-mlgraph>

Review explainer, and/or discuss and resolve blockers, design considerations e.g. "Build", "Build + Save".

  *   ⨀ webmachinelearning/webnn#807<https://github.com/webmachinelearning/webnn/issues/807>
  *   ☰ Explainer: WIP
  *   ⚙️ Initial implementation (Chromium + ORT): shiyi9801/chromium#227<https://github.com/shiyi9801/chromium/pull/227> (usage example<https://github.com/webmachinelearning/webnn-samples/compare/master...shiyi9801:webnn-samples:model_cache>)
  *   See also: 2025-05-22 discussion<https://www.w3.org/2025/05/22-webmachinelearning-minutes.html#98c6>

ℹ️ Query supported devices
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-05-wg-agenda.md#%E2%84%B9%EF%B8%8F-query-supported-devices>
After graph compilation (MLGraph.devices)
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-05-wg-agenda.md#after-graph-compilation-mlgraphdevices>

Discuss Chromium implementation feedback from Core ML, DirectML, TFLite backends.

Discuss and review proposed spec PR informed by the implementation.

  *   ⨀ webmachinelearning/webnn#836<https://github.com/webmachinelearning/webnn/issues/836>
  *   ⛙ webmachinelearning/webnn#854<https://github.com/webmachinelearning/webnn/pull/854>

Before graph compilation
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-05-wg-agenda.md#before-graph-compilation>

Discuss and review use cases.

  *   ⨀ webmachinelearning/webnn#815<https://github.com/webmachinelearning/webnn/issues/815>
  *   ⛙ Explainer use cases PR WIP

ℹ️ Core operator set
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-05-wg-agenda.md#%E2%84%B9%EF%B8%8F-core-operator-set>

(☝️ To be discussed subject to interest/new information:)

Revisit our core operator set effort that aims to identify current primitive gaps by mapping compositional fundamentals to WebNN operators.

Discuss any new information on rounding behavior across backends to understand feasibility for inclusion into the core operator set to help with e.g. quantization decomposition.

  *   ⨀ webmachinelearning/webnn#573<https://github.com/webmachinelearning/webnn/issues/573>
  *   ☰ Machine Learning Operator Mapping - All Raw Operators<https://onedrive.live.com/edit?id=EE82F5C6F06C7371!345450&resid=EE82F5C6F06C7371!345450&ithint=file%2Cxlsx&authkey=!AK8f-RDTleqlLXE&wdo=2&cid=ee82f5c6f06c7371>