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

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-02-12-wg-agenda.md


WebML WG Teleconference – 12 February 2026 - 15:00-16:00 UTC
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-02-12-wg-agenda.md#webml-wg-teleconference--12-february-2026---1500-1600-utc>

Important

⏰ Early morning warning for the West Coast.

See the timezone table ...
🤝 Logistics
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-02-12-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/2026/02/12-webmachinelearning-minutes.html


🧪 Incubations
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-02-12-wg-agenda.md#-incubations>
Dynamic AI Offloading Protocol
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-02-12-wg-agenda.md#dynamic-ai-offloading-protocol>

Update on the explainer and WebNN estimateQoS extension prototype. Discuss review feedback.

  *   ⨀ webmachinelearning/proposals#15<https://github.com/webmachinelearning/proposals/issues/15>
  *   ✅ Resolution<https://www.w3.org/2026/01/15-webmachinelearning-minutes.html#89af>

Last Week in Community Group
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-02-12-wg-agenda.md#last-week-in-community-group>

A debrief from WebML CG Teleconference – 5 February 2026<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-02-05-cg-agenda.md> (minutes<https://www.w3.org/2026/02/05-webmachinelearning-minutes.html>).

🧠 Web Neural Network API
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-02-12-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/>

🚀 Origin Trial launch
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-02-12-wg-agenda.md#-origin-trial-launch>

Celebrate WebNN Origin Trial launch on Chrome and Edge.

Review vendor-neutral WebNN Docs that assist early adopters on their Origin Trial journey. Discuss launch logistics and cross-vendor alignment.

  *   ☰ WebNN Docs: Origin Trials Registration<https://webnn.io/en/learn/get-started/ot_registration>
  *   ☰ WebNN Docs: Tutorials<https://webnn.io/en/learn/tutorials>

ℹ️ Power preferences and the fallback concept
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-02-12-wg-agenda.md#%E2%84%B9%EF%B8%8F-power-preferences-and-the-fallback-concept>

Agree on the proposed spec change to expand powerPreference enum with a new value "fallback" (prior "no-acceleration") conceptually aligned with WebGPU.

Agree on spec language to clarify the non-normative nature of these hints.

  *   ⨀ webmachinelearning/webnn#911<https://github.com/webmachinelearning/webnn/issues/911>

ℹ️ Dynamic dimensions
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-02-12-wg-agenda.md#%E2%84%B9%EF%B8%8F-dynamic-dimensions>

Review the MLDynamicDimension proposal and discuss any new information from prototyping.

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

ℹ️ Operator chaining
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-02-12-wg-agenda.md#%E2%84%B9%EF%B8%8F-operator-chaining>

Revisit operator chaining proposal with new information.

  *   ⨀ webmachinelearning/webnn#106<https://github.com/webmachinelearning/webnn/issues/106>

ℹ️ Get devices used for a graph after graph compilation
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-02-12-wg-agenda.md#%E2%84%B9%EF%B8%8F-get-devices-used-for-a-graph-after-graph-compilation>

ONNX Runtime is adding support for this feature backed by the proposed MLGraph.devices:

  *   ⨀ microsoft/onnxruntime#27167<https://github.com/microsoft/onnxruntime/issues/27167>

Seek consensus on the corresponding WebNN spec change:

  *   ⨀ webmachinelearning/webnn#836<https://github.com/webmachinelearning/webnn/issues/836>
  *   ⛙ webmachinelearning/webnn#854<https://github.com/webmachinelearning/webnn/pull/854>