WebML WG Teleconference – 21 May 2026 - 15:00-16:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-05-21-wg-agenda.md


WebML WG Teleconference – 21 May 2026 - 15:00-16:00 UTC
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-05-21-wg-agenda.md#webml-wg-teleconference--21-may-2026---1500-1600-utc>
See the timezone table ...
San Francisco   Thu, 21 May 2026        08:00
Boston  Thu, 21 May 2026        11:00
London  Thu, 21 May 2026        16:00
Berlin  Thu, 21 May 2026        17:00
Helsinki        Thu, 21 May 2026        18:00
Shanghai        Thu, 21 May 2026        23:00
Tokyo   Fri, 22 May 2026        00:00
UTC     Thu, 21 May 2026        15:00 UTC

Other locations: https://www.timeanddate.com/worldclock/fixedtime.html?iso=20260521T15


Logistics
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-05-21-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/2026/05/21-webmachinelearning-minutes.html


Web Neural Network API
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-05-21-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/>

Low-precision floating-point data types
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-05-21-wg-agenda.md#low-precision-floating-point-data-types>

Discuss survey results to inform the next steps.

  *   ⨀ webmachinelearning/webnn#930<https://github.com/webmachinelearning/webnn/issues/930>

Allow 0 size dimensions
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-05-21-wg-agenda.md#allow-0-size-dimensions>

Confirm implementability to unblock the feature.

  *   ⨀ webmachinelearning/webnn#391<https://github.com/webmachinelearning/webnn/issues/391>

Upper bounds on concat inputs and split outputs
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-05-21-wg-agenda.md#upper-bounds-on-concat-inputs-and-split-outputs>

Discuss and agree on future-proof upper bounds informed by real-world models.

  *   ⨀ webmachinelearning/webnn#931<https://github.com/webmachinelearning/webnn/issues/931>

Effective MLComputePolicy exposure
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-05-21-wg-agenda.md#effective-mlcomputepolicy-exposure>

Review the use cases and concrete proposal.

  *   ⨀ webmachinelearning/webnn#934<https://github.com/webmachinelearning/webnn/issues/934>

MLComputePolicy enhancements: "low-latency" and "precision"
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-05-21-wg-agenda.md#mlcomputepolicy-enhancements-low-latency-and-precision>

Discuss the proposed enhancements: "low-latency" for audio processing use case; "precision" to avoid chopping off low bits. Gauge interest.

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

PR queue cleanup
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-05-21-wg-agenda.md#pr-queue-cleanup>

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

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