WebML WG Teleconference – 10 March 2022 - 15:00-16:00 UTC+0

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-03-10-wg-agenda.md


WebML WG Teleconference – 10 March 2022 - 15:00-16:00 UTC+0
See the timezone table ...
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-03-10-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

  *   Call-in details: https://lists.w3.org/Archives/Member/internal-webmachinelearning/2020Apr/0000.html

  *   Minutes: https://www.w3.org/2022/03/10-webmachinelearning-minutes.html


________________________________
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-03-10-wg-agenda.md#%E2%84%B9%EF%B8%8F-security-considerations---last-call-for-review>ℹ️ Security considerations - last call for review
Review the group's response to security questions from Chrome Security team. Please record your feedback and comments in the issues and/or draft PR. Agree on the next step that is an "official" Security wide review.

  *    issue: General Security Questions: https://github.com/webmachinelearning/webnn/issues/241

  *    PR: Update Security Considerations per review feedback: https://github.com/webmachinelearning/webnn/pull/251

  *    All security-tracker issues: https://github.com/webmachinelearning/webnn/issues?q=label%3Asecurity-tracker+


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-03-10-wg-agenda.md#%E2%84%B9%EF%B8%8F--graph-execution-methods-used-in-different-threading-models-immediate-async-queued>ℹ️ Graph execution methods used in different threading models: immediate, async, queued

  *   Discuss and review the proposal for new Immediate Execution, Async Execution and Queued Execution interfaces. Discuss the relationship with WebNN/WebGPU interop investigation, needs to seek explicit review from the WebGPU WG.

  *    issue: Should WebNN support async APIs? https://github.com/webmachinelearning/webnn/issues/230

  *    PR: Define graph execution methods used in different threading models https://github.com/webmachinelearning/webnn/pull/255


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-03-10-wg-agenda.md#%E2%84%B9%EF%B8%8F-candidate-recommendation-proposed-new-features>ℹ️ Candidate Recommendation proposed new features
CR expectation is that the spec is considered technically complete and fit for purpose. Review the new proposed CR issues targeting this milestone. Discuss any blockers or new information that might suggest we need to adjust our scope and/or timeline.

Proposed new CR issues:

  *    WebNN should support int8 quantized models https://github.com/webmachinelearning/webnn/issues/128

  *    WebNN / WebGPU interop (currently tracked as part of #226) https://github.com/gpuweb/gpuweb/issues/2500


(All "cr" issues https://github.com/webmachinelearning/webnn/labels/cr)

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-03-10-wg-agenda.md#%E2%84%B9%EF%B8%8F-webnn-api-open-pull-requests>ℹ️ WebNN API open pull requests
Discuss/resolve issues in open PRs pending reviews:

  *   Open PRs: https://github.com/webmachinelearning/webnn/pulls