WebML WG Teleconference – 4 June 2026 - 15:00-16:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-06-04-wg-agenda.md


WebML WG Teleconference – 4 June 2026 - 15:00-16:00 UTC
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-06-04-wg-agenda.md#webml-wg-teleconference--4-june-2026---1500-1600-utc>
See the timezone table ...
San Francisco   Thu, 4 June 2026        08:00
Boston  Thu, 4 June 2026        11:00
London  Thu, 4 June 2026        16:00
Berlin  Thu, 4 June 2026        17:00
Helsinki        Thu, 4 June 2026        18:00
Shanghai        Thu, 4 June 2026        23:00
Tokyo   Fri, 5 June 2026        00:00
UTC     Thu, 4 June 2026        15:00 UTC

Other locations: https://www.timeanddate.com/worldclock/fixedtime.html?iso=20260604T15


Logistics
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-06-04-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/2026/06/04-webmachinelearning-minutes.html


Announcements
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-06-04-wg-agenda.md#announcements>
TPAC 2026
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-06-04-wg-agenda.md#tpac-2026>

Dublin, Ireland, 26-30 October 2026.

Web Neural Network API
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-06-04-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/>

Dynamic AI Offloading Protocol (DAOP) update
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-06-04-wg-agenda.md#dynamic-ai-offloading-protocol-daop-update>

Share learnings from the Dynamic AI Offloading Protocol (DAOP) incubation to inform related work on WebNN in QoS estimation, dynamic execution routing.

  *   ≡ https://github.com/webmachinelearning/daop


Effective MLComputePolicy
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-06-04-wg-agenda.md#effective-mlcomputepolicy>

Discuss new proposals, compilation metrics & runtime estimates, low latency v high throughput tradeoff implications on the design, strict hints to fail at build, "low-latency", "precision" hints.

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

Discrepancies with maxPool2d padding behavior
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-06-04-wg-agenda.md#discrepancies-with-maxpool2d-padding-behavior>

Discuss the edge case and potential solutions.

  *   ⨀ webmachinelearning/webnn#935<https://github.com/webmachinelearning/webnn/issues/935>

Composite operators / subgraphs
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-06-04-wg-agenda.md#composite-operators--subgraphs>

Discuss new feedback, review any data to understand the performance impact of possible op removal.

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

PR queue cleanup
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-06-04-wg-agenda.md#pr-queue-cleanup>

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

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