WebML WG Teleconference – 23 April 2026 - 15:00-16:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-04-23-wg-agenda.md


WebML WG Teleconference – 23 April 2026 - 15:00-16:00 UTC
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-04-23-wg-agenda.md#webml-wg-teleconference--23-april-2026---1500-1600-utc>
See the timezone table ...
San Francisco   Thu, 23 April 2026      08:00
Boston  Thu, 23 April 2026      11:00
London  Thu, 23 April 2026      16:00
Berlin  Thu, 23 April 2026      17:00
Helsinki        Thu, 23 April 2026      18:00
Shanghai        Thu, 23 April 2026      23:00
Tokyo   Fri, 24 April 2026      00:00
UTC     Thu, 23 April 2026      15:00 UTC

Other locations: https://www.timeanddate.com/worldclock/fixedtime.html?iso=20260423T15


🤝 Logistics
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-04-23-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/2026/04/23-webmachinelearning-minutes.html


🧠 Web Neural Network API
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-04-23-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/>

Lower limit for conv2d/pool2d kernel sizes, dilations, strides
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-04-23-wg-agenda.md#lower-limit-for-conv2dpool2d-kernel-sizes-dilations-strides>

Discuss edge cases that may cause integer overflows and the proposed mitigations.

  *   ⨀ webmachinelearning/webnn#928<https://github.com/webmachinelearning/webnn/issues/928>

conv2d output channels validation
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-04-23-wg-agenda.md#conv2d-output-channels-validation>

Discuss the issue and review the proposed spec change.

  *   ⨀ webmachinelearning/webnn#925<https://github.com/webmachinelearning/webnn/issues/925>

MLComputePolicy naming
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-04-23-wg-agenda.md#mlcomputepolicy-naming>

Discuss and agree on future-proof naming.

  *   ⛙ webmachinelearning/webnn#923<https://github.com/webmachinelearning/webnn/pull/923>

Bounded dynamic dimension
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-04-23-wg-agenda.md#bounded-dynamic-dimension>

Discuss framework support, backend dependent bounds.

  *   ⨀ webmachinelearning/webnn#883<https://github.com/webmachinelearning/webnn/issues/883>

WebNN PyTorch Exporter
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-04-23-wg-agenda.md#webnn-pytorch-exporter>

Discuss an experiment to export PyTorch models to the WebNN format.

  *   ☰ https://github.com/rustnn/torch2webnn

  *   ☰ .webnn file format webmachinelearning/proposals#16<https://github.com/webmachinelearning/proposals/issues/16>

PR queue cleanup
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-04-23-wg-agenda.md#pr-queue-cleanup>

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

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