WebML WG Teleconference – 18 December 2025 - 15:00-16:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-12-18-wg-agenda.md


WebML WG Teleconference – 18 December 2025 - 15:00-16:00 UTC
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-12-18-wg-agenda.md#webml-wg-teleconference--18-december-2025---1500-1600-utc>

Important

⏰ Early morning warning for the West Coast.

See the timezone table ...
🤝 Logistics
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-12-18-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/2025/12/18-webmachinelearning-minutes.html


🧪 Incubations
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-12-18-wg-agenda.md#-incubations>

A debrief from WebML CG Teleconference – 11 December 2025<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-12-11-cg-agenda.md> (minutes<https://www.w3.org/2025/12/11-webmachinelearning-minutes.html>).

🧠 Web Neural Network API
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-12-18-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/>

📢 New implementation experience and developer feedback
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-12-18-wg-agenda.md#-new-implementation-experience-and-developer-feedback>

Come join us for an unveiling of exciting new implementation experience. 🎁

We will also celebrate encouraging developer feedback<https://github.com/webmachinelearning/webnn/issues/763#issuecomment-3605012091> from early adopters and reflect the past year. 🎉

ℹ️ External weights, learnings from WebGPU
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-12-18-wg-agenda.md#%E2%84%B9%EF%B8%8F-external-weights-learnings-from-webgpu>

Continue discuss external weights for constants, optimization potential, pros and cons, other considerations.

Disseminate new information from WebGPU regarding data-streaming APIs and plain buffer uploads.

  *   ⨀ webmachinelearning/webnn#901<https://github.com/webmachinelearning/webnn/issues/901>
  *   ⨀ gpuweb/gpuweb#4185<https://github.com/gpuweb/gpuweb/issues/4185>

ℹ️ New device selection hints for MLContextOptions
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-12-18-wg-agenda.md#%E2%84%B9%EF%B8%8F-new-device-selection-hints-for-mlcontextoptions>

Discuss the suggestion to add new hints to complement MLPowerPreference.

Identify the minimal set of hints with strong use case backing, define defaults.

  *   ⨀ webmachinelearning/webnn#902<https://github.com/webmachinelearning/webnn/issues/902>
  *   ± MLContextOptions diff: webmachinelearning/webnn#902 (comment)<https://github.com/webmachinelearning/webnn/issues/902#issuecomment-3612503939>

ℹ️ Operator chaining
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-12-18-wg-agenda.md#%E2%84%B9%EF%B8%8F-operator-chaining>

Revisit operator chaining proposal with new information TBA.

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

ℹ️ Add minimum data type set and rank range for input, constant, output
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-12-18-wg-agenda.md#%E2%84%B9%EF%B8%8F-add-minimum-data-type-set-and-rank-range-for-input-constant-output>

  *   ⨀ webmachinelearning/webnn#896<https://github.com/webmachinelearning/webnn/issues/896>
  *   ⛙ webmachinelearning/webnn#910<https://github.com/webmachinelearning/webnn/pull/910>

Remove conformance tests with negative scale of DQ/Q operators
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-12-18-wg-agenda.md#remove-conformance-tests-with-negative-scale-of-dqq-operators>

  *   ⨀ webmachinelearning/webnn#879<https://github.com/webmachinelearning/webnn/issues/879>
  *   ⛙ webmachinelearning/webnn#906<https://github.com/webmachinelearning/webnn/pull/906>