WebML WG Teleconference – 19 June 2025 - 15:00-16:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-19-wg-agenda.md


WebML WG Teleconference – 19 June 2025 - 15:00-16:00 UTC
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-19-wg-agenda.md#webml-wg-teleconference--19-june-2025---1500-1600-utc>
See the timezone table ...
Logistics
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-19-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/2025/06/19-webmachinelearning-minutes.html


Agenda
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-19-wg-agenda.md#agenda>
📣 Announcements
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-19-wg-agenda.md#-announcements>

  *   ⚡ Awesome WebNN tools update
  *   💡 WebNN Documentation community preview
  *   🗓️ Web Almanac Generative AI 2025 chapter

🧪 Incubations
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-19-wg-agenda.md#-incubations>

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

🏷️ Operator specific issues
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-19-wg-agenda.md#%EF%B8%8F-operator-specific-issues>

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

  *   Drop support for int32/uint32 of zeropoint for quantizeLinear

     *   ⨀ webmachinelearning/webnn#856<https://github.com/webmachinelearning/webnn/issues/856>
  *   Add missing 64-bit integers support for some reduction operators

     *   ⨀ webmachinelearning/webnn#694<https://github.com/webmachinelearning/webnn/issues/694>
     *   ⛙ webmachinelearning/webnn#695<https://github.com/webmachinelearning/webnn/pull/695>
     *   ⨀ related: minimum data type set webmachinelearning/webnn#853<https://github.com/webmachinelearning/webnn/issues/853>

🏷️ Other issues
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-19-wg-agenda.md#%EF%B8%8F-other-issues>

  *   ⨀ Evaluate sustainability impact webmachinelearning/webnn#861<https://github.com/webmachinelearning/webnn/issues/861>

ℹ️ Open PRs
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-19-wg-agenda.md#%E2%84%B9%EF%B8%8F-open-prs>

Review open PRs that benefit from high-bandwidth discussion.

  *   ⛙ https://github.com/webmachinelearning/webnn/pulls


ℹ️ Caching mechanism for MLGraph
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-19-wg-agenda.md#%E2%84%B9%EF%B8%8F-caching-mechanism-for-mlgraph>

Review the explainer and address remaining feedback. Agree on the next steps for the spec and implementation.

  *   ⨀ webmachinelearning/webnn#807<https://github.com/webmachinelearning/webnn/issues/807>
  *   ⛙ webmachinelearning/webnn#862<https://github.com/webmachinelearning/webnn/pull/862>
  *   ☰ Explainer preview https://github.com/webmachinelearning/webnn/blob/cache-explainer/cache-explainer.md

  *   ⚙️ Prototype implementation 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>)

ℹ️ Query supported devices
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-19-wg-agenda.md#%E2%84%B9%EF%B8%8F-query-supported-devices>
Before graph compilation
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-19-wg-agenda.md#before-graph-compilation>

Discuss product-driven use case feedback from Google Meet and translate into explainer updates.

Agree on the next steps toward a query mechanism that satisfies key requirements, define explainer and spec changes, if any.

  *   ⨀ Google Meet feedback: webmachinelearning/webnn#815 (comment)<https://github.com/webmachinelearning/webnn/issues/815#issuecomment-2962608053>
  *   ☰ Device Preference use cases: device-selection-explainer.md<https://github.com/webmachinelearning/webnn/blob/main/device-selection-explainer.md#device-preference-use-cases>
  *   ⛙ HW acceleration selection principles PR: webmachinelearning/webnn#860<https://github.com/webmachinelearning/webnn/pull/860>

After graph compilation (MLGraph.devices)
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-19-wg-agenda.md#after-graph-compilation-mlgraphdevices>

Call for use cases. Review any use case input.

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

ℹ️ Core operator set, current thinking
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-06-19-wg-agenda.md#%E2%84%B9%EF%B8%8F-core-operator-set-current-thinking>

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

Discuss "current thinking" topics and solicit feedback.

  *   ⨀ "current thinking" webmachinelearning/webnn#573 (comment)<https://github.com/webmachinelearning/webnn/issues/573#issuecomment-2469503466>
  *   ☰ 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>