WebML WG Teleconference – 8 August 2024 - 14:00-15:00 UTC

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


WebML WG Teleconference – 8 August 2024 - 14:00-15:00 UTC
<https://github.com/webmachinelearning/meetings/new/main/telcons#webml-wg-teleconference--8-august-2024---1400-1500-utc>
See the timezone table ...

Logistics
<https://github.com/webmachinelearning/meetings/new/main/telcons#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/2024/08/08-webmachinelearning-minutes.html


Agenda
<https://github.com/webmachinelearning/meetings/new/main/telcons#agenda>

ℹ️ TPAC 2024 registration and WebML WG F2F agenda building
<https://github.com/webmachinelearning/meetings/new/main/telcons#%E2%84%B9%EF%B8%8F-tpac-2024-registration-and-webml-wg-f2f-agenda-building>


W3C TPAC 2024 takes place in Anaheim, CA, USA at the Hilton Anaheim on 23–27 September 2024. The WebML WG will meet F2F on Monday, 23 September 2024, 09:00–18:00 PDT.


Important

  *   Please complete the registration form: https://www.w3.org/2024/09/TPAC/#registration

     *   For remote participation, please choose the "I will attend remotely" option.
     *   Note on fee waivers: https://www.w3.org/2024/09/TPAC/registration.html#waiver

  *   Review the in development F2F agenda and provide your suggestions: #25<https://github.com/webmachinelearning/meetings/issues/25>

________________________________
ℹ️ Transformers.js update takeaways
<https://github.com/webmachinelearning/meetings/new/main/telcons#%E2%84%B9%EF%B8%8F-transformersjs-update-takeaways>


We received an exciting and action-packed Transformers.js update presentation from Joshua Lochner on our June call. As a refresher, please check the animated presentation below.


Tip

We'll revisit the feedback from this framework customer to ensure it is reflected in our WebNN work, issues and priorities appropriately.


  *   Transformers.js June 2024 update<https://docs.google.com/presentation/d/1BCkLdzB5cR1ZfHwFXkIDuV8BCw8-KIWICbsZ1O00H2Q/view> (PDF snapshot<https://lists.w3.org/Archives/Public/www-archive/2024Jun/att-0004/Transformers.js-update.pdf>), minutes with Q&A<https://www.w3.org/2024/06/27-webmachinelearning-minutes.html#t04>

________________________________
ℹ️ Device selection + quantization & dequantization
<https://github.com/webmachinelearning/meetings/new/main/telcons#%E2%84%B9%EF%B8%8F-device-selection--quantization--dequantization>


📌 We agreed to evolve MLContextOptions and other API controls for device selection informed by further implementation experience and new use cases from the wider web community. To assist in this effort, the "npu" device type landed in Chromium and samples for fp16 models with NPU device type have been made available for experimentation.


Tip

We'll continue solicit feedback on future-proof device selection abstractions: fallback device, multiple devices in a preferred order, an exclusion of a specific device, interaction with quantization & dequantization (QDQ) data types.


  *   ⛭ Chromium NPU device type: https://chromium-review.googlesource.com/c/chromium/src/+/5330647

  *   ⛭ NPU + fp16 samples: image classification<https://webmachinelearning.github.io/webnn-samples/image_classification/>, object detection<https://webmachinelearning.github.io/webnn-samples/object_detection/>
  *   Current device selection mechanism: device selection<https://www.w3.org/TR/webnn/#programming-model-device-selection>, MLContextOptions<https://www.w3.org/TR/webnn/#dictdef-mlcontextoptions>
  *   GitHub discussion:
     *   ⨀ webmachinelearning/webnn#623<https://github.com/webmachinelearning/webnn/issues/623>
     *   ⛙ webmachinelearning/webnn#696<https://github.com/webmachinelearning/webnn/pull/696>

________________________________
ℹ️ MLBuffer
<https://github.com/webmachinelearning/meetings/new/main/telcons#%E2%84%B9%EF%B8%8F-mlbuffer>


📌 A placeholder for discussion on active MLBuffer topics as appropriate.

  *   ⨀ webmachinelearning/webnn#688<https://github.com/webmachinelearning/webnn/issues/688>
  *   ⨀ webmachinelearning/webnn#697<https://github.com/webmachinelearning/webnn/issues/697>
  *   🏷️ All webgpu interop<https://github.com/webmachinelearning/webnn/labels/webgpu%20interop> issues

________________________________
ℹ️ TAG feedback on resource contention considerations closure
<https://github.com/webmachinelearning/meetings/new/main/telcons#%E2%84%B9%EF%B8%8F-tag-feedback-on-resource-contention-considerations-closure>


The group provided the TAG a satisfactory response to their resource contention consideration issue.


Tip

The group is now expected to close the loop by adding non-normative text for DoS vectors and mitigations (PRs welcome!), multi-implementer support feedback proposed to be addressed by making implementation experience<https://webmachinelearning.github.io/webnn-status/> more visible in the spec.


  *   ⨀ w3ctag/design-reviews#933 (comment)<https://github.com/w3ctag/design-reviews/issues/933#issuecomment-2126805061>
  *   ⨀ Related: webmachinelearning/webnn#529<https://github.com/webmachinelearning/webnn/issues/529>
  *   ☰ Related: WebGPU DoS https://www.w3.org/TR/webgpu/#security-dos


________________________________
ℹ️ Open issues and PRs
<https://github.com/webmachinelearning/meetings/new/main/telcons#%E2%84%B9%EF%B8%8F-open-issues-and-prs>


The group made significant progress during July. Thank you!


We'll discuss new issues, debrief the group on merged PRs and review open PRs since our last meeting:

  *   ⨀ All open issues<https://github.com/webmachinelearning/webnn/issues>
  *   ⛙ All open pull requests<https://github.com/webmachinelearning/webnn/pulls>
  *   ⛙ Recently merged PRs<https://github.com/webmachinelearning/webnn/pulls?q=is%3Apr+is%3Amerged>


Priority is given to issues and PRs proposed for discussion in this meetings issue ahead the meeting:

  *   🆕 #26<https://github.com/webmachinelearning/meetings/issues/26>