WebML WG Teleconference – 19 December 2024 - meeting minutes & Happy Holidays!

Hi All,

Thanks for joining us!

Minutes:
https://www.w3.org/2024/12/19-webmachinelearning-minutes.html

Summary:

  1.  WebML Working Group Charter update<https://www.w3.org/2024/12/19-webmachinelearning-minutes.html#480e>
     *   Current WG Charter<https://www.w3.org/2024/12/19-webmachinelearning-minutes.html#702c>
     *   Model Loader API, keep as tentative or remove from scope?<https://www.w3.org/2024/12/19-webmachinelearning-minutes.html#818b>
     *   Core operator set, scope and coordination<https://www.w3.org/2024/12/19-webmachinelearning-minutes.html#e6d2>
     *   Task-based APIs and Prompt API<https://www.w3.org/2024/12/19-webmachinelearning-minutes.html#5fc8>
     *   Speech Synthesis<https://www.w3.org/2024/12/19-webmachinelearning-minutes.html#a111>
     *   On-device training<https://www.w3.org/2024/12/19-webmachinelearning-minutes.html#88cf>
     *   Charter development timeline<https://www.w3.org/2024/12/19-webmachinelearning-minutes.html#0232>
  2.  Device selection abstractions update<https://www.w3.org/2024/12/19-webmachinelearning-minutes.html#02d1>
  3.  WebNN Operator Update Wave 3<https://www.w3.org/2024/12/19-webmachinelearning-minutes.html#fb67>
  4.  Core op set: MLIR Linalg findings revisited<https://www.w3.org/2024/12/19-webmachinelearning-minutes.html#ffff>
  5.  Get to know Task-specific APIs and Prompt API<https://www.w3.org/2024/12/19-webmachinelearning-minutes.html#7ec8>
  6.  Happy Holidays!<https://www.w3.org/2024/12/19-webmachinelearning-minutes.html#42b0>

Thank You everyone for your significant contributions during 2024! Our Working Group accomplished a lot this year, a few highlights:

- WebNN API evolved driven by research into popular more advanced models, more diverse implementations
- WebNN API Candidate Rec Snapshot milestone was met in 2Q 2024
- the WG made in total ~100 spec publications and merged +180 PRs this year
- many new active contributors joined, Dwayne as a co-editor, the group grew and diversified further
- we converged on new API abstractions for tensors, device selection, defined op set principles
- we improved the spec quality significantly with expert advice
- we organized our first F2F in Anaheim and it was a blast
- we made strong progress on the implementations across 3 backends, XPUs, multiple OSes
- we witnessed positive buzz in the tech industry around WebNN, made a few keynote appearances
- a lot of exciting demos and samples were published, wpt test coverage improved
- and much more!

We're entering an exciting phase of development in 2025:

- the WebNN API is expected to get in the hands of more developers for large-scale trials, and more
- feedback from developers and users will help guide our priorities

Happy Holidays everyone -- please relax, disconnect, and recharge.

See you on our next call 16 Jan 2025!

Thanks,

-Anssi (WebML WG/CG chair)