WebML WG Teleconference – 12 March 2026 - 15:00-16:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-03-12-wg-agenda.md


WebML WG Teleconference – 12 March 2026 - 15:00-16:00 UTC
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-03-12-wg-agenda.md#webml-wg-teleconference--12-march-2026---1500-1600-utc>

Important

⏰ Please note Daylight Saving Time<https://www.timeanddate.com/time/dst/2026a.html> changes apply to this meeting in some regions. The timezone table below reflects that.

See the timezone table ...
San Francisco   Thu, 12 March 2026      08:00
Boston  Thu, 12 March 2026      11:00
London  Thu, 12 March 2026      15:00
Berlin  Thu, 12 March 2026      16:00
Helsinki        Thu, 12 March 2026      17:00
Shanghai        Thu, 12 March 2026      23:00
Tokyo   Fri, 13 March 2026      00:00
UTC     Thu, 12 March 2026      15:00 UTC

Other locations: https://www.timeanddate.com/worldclock/fixedtime.html?iso=20260312T15


🤝 Logistics
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-03-12-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: internal-webmachinelearning<https://lists.w3.org/Archives/Member/internal-webmachinelearning/2023Jun/0000.html>
  *   Minutes: https://www.w3.org/2026/03/12-webmachinelearning-minutes.html


🧪 Incubations
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-03-12-wg-agenda.md#-incubations>
Dynamic AI Offloading Protocol
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-03-12-wg-agenda.md#dynamic-ai-offloading-protocol>

Review and approve the initial PR as the baseline for further incubation.

  *   ⛙ webmachinelearning/daop#1<https://github.com/webmachinelearning/daop/pull/1>
  *   ☰ 2026-02-12 review feedback<https://www.w3.org/2026/02/12-webmachinelearning-minutes.html#1e1f>
  *   ✅ 2026-01-15 resolution<https://www.w3.org/2026/01/15-webmachinelearning-minutes.html#89af>

WebNN Graph DSL and Portable File Format
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-03-12-wg-agenda.md#webnn-graph-dsl-and-portable-file-format>

Review and discuss use cases for the proposed WebNN graph DSL and portable file format.

  *   ⨀ webmachinelearning/proposals#16<https://github.com/webmachinelearning/proposals/issues/16>

🧠 Web Neural Network API
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-03-12-wg-agenda.md#-web-neural-network-api>

Tip

Specification<https://www.w3.org/TR/webnn/> | Explainer<https://github.com/webmachinelearning/webnn/blob/main/explainer.md> | Implementation Report<https://wpt.fyi/results/webnn> | Implementation Status<https://webmachinelearning.github.io/webnn-status/>

Public API surface reduction investigation
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-03-12-wg-agenda.md#public-api-surface-reduction-investigation>

Discuss the proposal to reduce the public API surface with a subgraph operator library.

  *   ⨀ webmachinelearning/webnn#907<https://github.com/webmachinelearning/webnn/issues/907>

Generalize/relax the normalize* ops
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-03-12-wg-agenda.md#generalizerelax-the-normalize-ops>

Improves cohesion with other ops that are expected to drop the 2D suffix.

  *   ⨀ webmachinelearning/webnn#490<https://github.com/webmachinelearning/webnn/issues/490>
  *   ⨀ webmachinelearning/webnn#904<https://github.com/webmachinelearning/webnn/issues/904>

Create a context in-parallel steps refinement
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-03-12-wg-agenda.md#create-a-context-in-parallel-steps-refinement>

Discuss the proposed fix to align with the latest in-parallel steps conventions.

  *   ⨀ webmachinelearning/webnn#919<https://github.com/webmachinelearning/webnn/issues/919>

Power preferences and the fallback concept
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-03-12-wg-agenda.md#power-preferences-and-the-fallback-concept>

Review the latest IDL.

  *   ⨀ webmachinelearning/webnn#911 (comment)<https://github.com/webmachinelearning/webnn/issues/911#issuecomment-3897412058>

WPT runners improvements for testing on GPU devices
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-03-12-wg-agenda.md#wpt-runners-improvements-for-testing-on-gpu-devices>

Discuss WPT runner improvements for GPUs, prior WebGPU CTS learnings. A sponsorship opportunity.

  *   ⨀ gpuweb/cts#2252<https://github.com/gpuweb/cts/issues/2252>

PR queue cleanup
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-03-12-wg-agenda.md#pr-queue-cleanup>

Approve and merge PRs ahead the meeting, discuss any blockers only.

  *   ⛙ webmachinelearning/webnn#906<https://github.com/webmachinelearning/webnn/pull/906>
  *   ⛙ webmachinelearning/webnn#910<https://github.com/webmachinelearning/webnn/pull/910>
  *   ⛙ webmachinelearning/webnn#916<https://github.com/webmachinelearning/webnn/pull/916>