WebML WG Teleconference – 8 February 2024 - 15:00-16:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-02-08-wg-agenda.md


WebML WG Teleconference – 8 February 2024 - 15:00-16:00 UTC
See the timezone table ...
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-02-08-wg-agenda.md#logistics>Logistics

  *   Chair: Anssi
  *   Scribe: ? (see howto<https://github.com/webmachinelearning/meetings/blob/main/scribe-howto.md>, volunteers welcome!)
  *   IRC: irc://irc.w3.org:6667/#webmachinelearning

  *   IRC web client: https://irc.w3.org/?channels=#webmachinelearning

  *   Joining instructions: https://lists.w3.org/Archives/Member/internal-webmachinelearning/2023Jun/0000.html

  *   Minutes: https://www.w3.org/2024/02/08-webmachinelearning-minutes.html


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-02-08-wg-agenda.md#agenda>Agenda
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-02-08-wg-agenda.md#%E2%84%B9%EF%B8%8F-webnn-api-delta-wide-review-and-cr-snapshot-readiness>ℹ️ WebNN API delta wide review and CR Snapshot readiness

Status: We're on track. We initiated Architecture/TAG and Privacy delta wide reviews highlighting relevant new information and informed other horizontal groups (a11y, i18n, Security) of the plan to publish a new CR Snapshot during Q1'24.

We'll discuss any review feedback received.

  *   Wide review tracker webmachinelearning/webnn#239<https://github.com/webmachinelearning/webnn/issues/239>

We also review CR Snapshot readiness and discuss any open issues:

  *   CR readiness & requirements webmachinelearning/webnn#240<https://github.com/webmachinelearning/webnn/issues/240>
  *   Proposed high-level status webmachinelearning/webnn#532<https://github.com/webmachinelearning/webnn/pull/532>

References:

  *   WebNN publication history<https://www.w3.org/standards/history/webnn/> and diff between CR Snapshot 30 Mar 2023 and latest<https://services.w3.org/htmldiff?doc1=https%3A%2F%2Fwww.w3.org%2FTR%2F2023%2FCR-webnn-20230330%2F&doc2=https%3A%2F%2Fwww.w3.org%2FTR%2Fwebnn%2F>
  *   (Informative) Wide Review<https://www.w3.org/2023/Process-20231103/#wide-review> and CR Snapshot<https://www.w3.org/2023/Process-20231103/#publishing-crrs> requirements

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-02-08-wg-agenda.md#%E2%84%B9%EF%B8%8F-issue-prioritization-contd>ℹ️ Issue prioritization (cont'd)

Review and discuss the proposed issue triage guidance. The aim of this exercise is to make the entire group more productive and also help new contributors get started and focus their contributions. Call for volunteers to join the triage team.

  *   Proposed triage guidance and new labels: webmachinelearning/webnn#533<https://github.com/webmachinelearning/webnn/pull/533>
  *   Current labels: https://github.com/webmachinelearning/webnn/labels


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-02-08-wg-agenda.md#%E2%84%B9%EF%B8%8F-new-features>ℹ️ New features
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-02-08-wg-agenda.md#mlbuffer>MLBuffer

Continue discussion on the proposal for a backend-agnostic storage type for WebNN operations informed by implementation experience. Please pay attention to the open questions in the sub-issues.

  *    MLBuffer proposal: webmachinelearning/webnn#482<https://github.com/webmachinelearning/webnn/issues/482>

     *    Creation and representing MLBuffer on XPU devices webmachinelearning/webnn#542<https://github.com/webmachinelearning/webnn/issues/542>
     *    Uploading/downloading tensor data webmachinelearning/webnn#543<https://github.com/webmachinelearning/webnn/issues/543>
     *    Support for MLBuffer in graph execution webmachinelearning/webnn#544<https://github.com/webmachinelearning/webnn/issues/544>
  *    Chromium implementation: https://chromium-review.googlesource.com/c/chromium/src/+/5173676


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-02-08-wg-agenda.md#pull-request-review>Pull Request review

Review open PRs: https://github.com/webmachinelearning/webnn/pulls


Other open issues discussed subject to time based on your feedback.