WebML WG Teleconference – 28 August 2025 - 15:00-16:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-08-28-wg-agenda.md


WebML WG Teleconference – 28 August 2025 - 15:00-16:00 UTC
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-08-28-wg-agenda.md#webml-wg-teleconference--28-august-2025---1500-1600-utc>
See the timezone table ...
Logistics
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-08-28-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/2025/08/28-webmachinelearning-minutes.html


🧪 Incubations: Built-in AI APIs & agentic web
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-08-28-wg-agenda.md#-incubations-built-in-ai-apis--agentic-web>

Share recent WebML Community Group developments to keep the Working Group abreast of incubation progress: CG charter update, WebMCP explainer next steps, key open issues:

  *   WebML CG Charter update: review by 2025-09-18<https://lists.w3.org/Archives/Public/public-webmachinelearning/2025Aug/0005.html>
  *   WebMCP: explainer<https://github.com/webmachinelearning/webmcp/blob/main/docs/explainer.md>, proposal<https://github.com/webmachinelearning/webmcp/blob/main/docs/proposal.md>, open issues<https://github.com/webmachinelearning/webmcp/issues>

ℹ️ Query supported devices
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-08-28-wg-agenda.md#%E2%84%B9%EF%B8%8F-query-supported-devices>

  *   Before graph compilation

     *   ☰ Review the most recent proposal to expose CPU fallback + "accelerated" context creation hint
     *   ⨀ webmachinelearning/webnn#815 (comment)<https://github.com/webmachinelearning/webnn/issues/815#issuecomment-3198261369>
     *   ⛙ PR to be reviewed subject to availability
  *   After graph compilation

     *   ☰ Review the demo app (plan) and assess the hypothetical use cases
     *   ⨀ webmachinelearning/webnn#836<https://github.com/webmachinelearning/webnn/issues/836>
     *   ⛙ webmachinelearning/webnn#854<https://github.com/webmachinelearning/webnn/pull/854>

🏷️ Operator specific issues
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-08-28-wg-agenda.md#%EF%B8%8F-operator-specific-issues>

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

  *   Dynamic shapes

     *   ☰ Discuss requirements, known implementation limitations, best practices from native frameworks
     *   ⨀ issue TBD
  *   Support uint8/int8 input for resample2d

     *   ☰ Discuss WIP framework and native ML API support survey results
     *   ⨀ webmachinelearning/webnn#872<https://github.com/webmachinelearning/webnn/issues/872>
  *   Normalize the behavior when NaN is used for minValue or maxValue of clamp operator

     *   ⨀ webmachinelearning/webnn#874<https://github.com/webmachinelearning/webnn/issues/874>
     *   ⛙ PR to be reviewed subject to availability

🏷️ Wide review closure
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-08-28-wg-agenda.md#%EF%B8%8F-wide-review-closure>

We're almost done with our 2025 wide review cycle, tick the boxes on the remaining work:

  *    Privacy review: opSupportLimits() privacy considerations

     *   ⨀ webmachinelearning/webnn#875<https://github.com/webmachinelearning/webnn/issues/875>
     *   ⛙ webmachinelearning/webnn#881<https://github.com/webmachinelearning/webnn/pull/881>
  *    Security review (pending security reviewers' feedback)

     *   ⨀ w3c/security-request#85<https://github.com/w3c/security-request/issues/85>

ℹ️ Open PRs
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-08-28-wg-agenda.md#%E2%84%B9%EF%B8%8F-open-prs>

Review any open PRs that benefit from high-bandwidth discussion.

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