WebML CG Teleconference – 4 May 2022 - 04:00-05:00 UTC+0

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-05-04-cg-agenda.md


WebML CG Teleconference – 4 May 2022 - 04:00-05:00 UTC+0
See the timezone table ...
San Francisco (U.S.A. - California)     Tue, 5 April 2022       21:00   UTC-7 hours
Boston (U.S.A. - Massachusetts) Wed, 6 April 2022       00:00   UTC-4 hours
London (United Kingdom - England)       Wed, 6 April 2022       05:00   UTC+1 hours
Berlin (Germany)        Wed, 6 April 2022       06:00   UTC+2 hours
Helsinki (Finland)      Wed, 6 April 2022       07:00   UTC+3 hours
Shanghai (China)        Wed, 6 April 2022       12:00   UTC+8 hours
Tokyo (Japan)   Wed, 6 April 2022       13:00   UTC+9 hours
Sydney (Australia)      Wed, 6 April 2022       14:00   UTC+10 hours
Corresponding UTC (GMT) Wed, 6 April 2022       04:00 UTC

Other locations: https://www.timeanddate.com/worldclock/fixedtime.html?iso=20220504T04


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-05-04-cg-agenda.md#logistics>Logistics

  *   Chair: Anssi
  *   Scribe: ? (howto<https://github.com/webmachinelearning/meetings/blob/main/scribe-howto.md>)
  *   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/2022/05/04-webmachinelearning-minutes.html


________________________________
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-05-04-cg-agenda.md#agenda>Agenda

⚠️ On our 6 April 2022 call<https://www.w3.org/2022/04/06-webmachinelearning-minutes.html#t01> we agreed to move back to the 4:00 UTC meeting slot starting from this call.

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-05-04-cg-agenda.md#%E2%84%B9%EF%B8%8F-model-loader-api---new-issues>ℹ️ Model Loader API - new issues
Discuss and triage new issues; identify any reusable constructs, concepts and patterns to be shared with WebNN API.

  *   DevicePreference: "GPU" => "GpuRequired" and "GpuPreferred" webmachinelearning/model-loader#35<https://github.com/webmachinelearning/model-loader/issues/35>
  *   "default" v.s. "auto" in MLDevicePreference and MLPowerPreference webmachinelearning/model-loader#30<https://github.com/webmachinelearning/model-loader/issues/30>
  *   Add performance/usage Hints webmachinelearning/model-loader#34<https://github.com/webmachinelearning/model-loader/issues/34>

See 6 Apr 2022 minutes<https://www.w3.org/2022/04/06-webmachinelearning-minutes.html#t05> where we touched these topics quickly.

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-05-04-cg-agenda.md#%E2%84%B9%EF%B8%8F-model-loader-api---recap-earlier-issues>ℹ️ Model Loader API - recap earlier issues
Revisit the topics from earlier syncs for any updates from the community.

  *   Versioning webmachinelearning/model-loader#25<https://github.com/webmachinelearning/model-loader/issues/25>
  *   Streaming inputs webmachinelearning/model-loader#26<https://github.com/webmachinelearning/model-loader/issues/26>
  *   Standard model format webmachinelearning/model-loader#28<https://github.com/webmachinelearning/model-loader/issues/28>
  *   Support for non-IEEE 754 float point types webmachinelearning/model-loader#23<https://github.com/webmachinelearning/model-loader/issues/23>

See 9 Mar 2022 minutes<https://www.w3.org/2022/03/09-webmachinelearning-minutes.html> for the previous discussion.

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-05-04-cg-agenda.md#%E2%84%B9%EF%B8%8F-joint-cg-and-wg-brainstorming-session>ℹ️ Joint CG and WG brainstorming session
Let's use this slot to chat more informally on any topics of shared interest in this space to cross-pollinate and brainstorm across WebML CG<https://www.w3.org/groups/cg/webmachinelearning/participants> and WebML WG participants<https://www.w3.org/groups/wg/webmachinelearning/participants>, get to know each other better. Bring you own ideas, questions, suggestions. No restrictions other than adherence to our Code of Conduct<https://www.w3.org/Consortium/cepc/>. This chat will not be minuted.
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-05-04-cg-agenda.md#%E2%84%B9%EF%B8%8F-references>ℹ️ References

  *   WebML CG Teleconference - 6 Apr 2022 minutes<https://www.w3.org/2022/04/06-webmachinelearning-minutes.html>
  *   WebML CG Teleconference – 9 Mar 2022 minutes<https://www.w3.org/2022/03/09-webmachinelearning-minutes.html>
  *   WebML CG Teleconference – 9 Feb 2022 minutes<https://www.w3.org/2022/02/09-webmachinelearning-minutes.html>
  *   WebML CG Teleconference – 12 Jan 2022 minutes<https://www.w3.org/2022/01/12-webmachinelearning-minutes.html>
  *   Model Loader API explainer<https://github.com/webmachinelearning/model-loader/blob/main/explainer.md> and early spec draft<https://webmachinelearning.github.io/model-loader/>