WebML WG Teleconference – 11 August 2022 - 14:00-15:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-08-11-wg-agenda.md


WebML WG Teleconference – 11 August 2022 - 14:00-15:00 UTC
San Francisco (U.S.A. - California)     Thu, 11 August 2022     07:00   UTC-7 hours
Boston (U.S.A. - Massachusetts) Thu, 11 August 2022     10:00   UTC-4 hours
London (United Kingdom - England)       Thu, 11 August 2022     15:00   UTC+1 hours
Berlin (Germany)        Thu, 11 August 2022     16:00   UTC+2 hours
Helsinki (Finland)      Thu, 11 August 2022     17:00   UTC+3 hours
Shanghai (China)        Thu, 11 August 2022     22:00   UTC+8 hours
Tokyo (Japan)   Thu, 11 August 2022     23:00   UTC+9 hours
Corresponding UTC (GMT) Thu, 11 August 2022     14:00 UTC

Other locations: https://www.timeanddate.com/worldclock/fixedtime.html?iso=20220811T14


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-08-11-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/2020Apr/0000.html

  *   Minutes: https://www.w3.org/2022/08/11-webmachinelearning-minutes.html


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-08-11-wg-agenda.md#%E2%84%B9%EF%B8%8F-privacy-review-response-and-questions-from-ping>ℹ️ Privacy review response and questions from PING
Review the PING review response, solicit input from WG participants to questions PING raised.

  *    [privacy-request] Web Neural Network API w3cping/privacy-request#96<https://github.com/w3cping/privacy-request/issues/96>

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-08-11-wg-agenda.md#%E2%84%B9%EF%B8%8F-webgpu-and-wgsl-wide-review-request>ℹ️ WebGPU and WGSL wide review request
WebGPU WG invites WebML WG to review the latest versions of the WebGPU API and WGSL specs. Integration of WebGPU with WebNN is being tracked in [1], with possible WebGPU adjustments considered for a future revision of the specification. If breaking changes seem warranted to interoperate with WebNN, the GPU for the Web Working Group would be keen on hearing requirements.

  *   Review request https://lists.w3.org/Archives/Public/public-webmachinelearning-wg/2022Jul/0000.html

  *   WebGPU: https://www.w3.org/TR/webgpu/

  *   WGSL: https://www.w3.org/TR/WGSL/

  *   [1] gpuweb/gpuweb#2500<https://github.com/gpuweb/gpuweb/issues/2500>

Related:

  *    issue: CommandBuffer usage clarification: internal, external, both? webmachinelearning/webnn#264<https://github.com/webmachinelearning/webnn/issues/264>

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-08-11-wg-agenda.md#%E2%84%B9%EF%B8%8F-webnn-api-candidate-recommendation-open-issues>ℹ️ WebNN API Candidate Recommendation open issues
Review and discuss the current CR issues, work out a plan to address the issues prior to the expected CR publication.

  *   Current CR issues https://github.com/webmachinelearning/webnn/issues?q=is%3Aissue+is%3Aopen+label%3Acr


  *   Support asynchronous context creation

     *    issue: webmachinelearning/webnn#272<https://github.com/webmachinelearning/webnn/issues/272>
     *    PR: webmachinelearning/webnn#274<https://github.com/webmachinelearning/webnn/pull/274>
  *   Define ULP (unit of least precision) tolerances for testing

     *    issue: webmachinelearning/webnn#265<https://github.com/webmachinelearning/webnn/issues/265>
     *    PR: web-platform-tests/wpt#34287<https://github.com/web-platform-tests/wpt/pull/34287>
  *   Support for int8 quantized models

     *    issue: webmachinelearning/webnn#128<https://github.com/webmachinelearning/webnn/issues/128>
  *   Add method steps to operations

     *    issue: webmachinelearning/webnn#210<https://github.com/webmachinelearning/webnn/issues/210>

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-08-11-wg-agenda.md#%E2%84%B9%EF%B8%8F-proposed-new-features>ℹ️ Proposed new features

  *    issue: Remove the support of negative dimension values webmachinelearning/webnn#279<https://github.com/webmachinelearning/webnn/issues/279>

  *    issue: l2Pool2d algorithm clarifications webmachinelearning/webnn#278<https://github.com/webmachinelearning/webnn/issues/278>

Revisit proposed new features discussed earlier:

  *    issue: Should MLBufferView + MLOperandDescriptor be strongly typed webmachinelearning/webnn#275<https://github.com/webmachinelearning/webnn/issues/275>

  *    issue: Support coordinate transformation modes for Resample2d webmachinelearning/webnn#270<https://github.com/webmachinelearning/webnn/issues/270>

  *    issue: Define the data type of the padding, strides and dilations webmachinelearning/webnn#269<https://github.com/webmachinelearning/webnn/issues/269>

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-08-11-wg-agenda.md#%E2%84%B9%EF%B8%8F-tpac-2022>ℹ️ TPAC 2022
Discuss TPAC 2022<https://www.w3.org/2022/09/TPAC/Overview.html> plans for the WG.

  *   WebML WG Hybrid Meeting at TPAC 2022 #20<https://github.com/webmachinelearning/meetings/issues/20>