WebML WG Teleconference – 7 March 2024 - 15:00-16:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-07-wg-agenda.md


WebML WG Teleconference – 7 March 2024 - 15:00-16:00 UTC
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-07-wg-agenda.md#webml-wg-teleconference--7-march-2024---1500-1600-utc>
See the timezone table ...
Logistics
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-07-wg-agenda.md#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/2024/03/07-webmachinelearning-minutes.html


Agenda
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-07-wg-agenda.md#agenda>
ℹ️ Call for Consensus: WebNN API CR Snapshot
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-07-wg-agenda.md#%E2%84%B9%EF%B8%8F-call-for-consensus-webnn-api-cr-snapshot>

On 28 Feb 2024 we issued a Call for Consensus (CfC) to publish the Web Neural Network API as a new Candidate Recommendation Snapshot (CRS).

We'll review CfC results and if satisfied initiate a transition request to get the publication machinery moving.

  *   Call for Consensus<https://lists.w3.org/Archives/Public/public-webmachinelearning-wg/2024Feb/0006.html> open until 7 Mar 2024

ℹ️ Hybrid AI exploration
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-07-wg-agenda.md#%E2%84%B9%EF%B8%8F-hybrid-ai-exploration>

💬 Format: presentation + Q&A

An exploration into hybrid approaches that could flexibly shift ML workloads between server and client to support elasticity and avoid the problem of developers targeting only the weakest clients’ capabilities.

The project team will give a 20-min presentation followed by a Q&A to introduce the problem statement, initial proposed requirements, goals, non-goals, with an eye on the intersect beneficial to the WebNN API.

Expected outcome: Project team receives feedback from this group to help inform the direction of the exploration: past learnings, issue priorities, relevant data points, dos and don'ts all welcome.

Note: Any concrete proposals from this exploration that impact Web APIs are expected to be incubated in applicable Community Group(s) subject to agreement.

References:

  *   Hybrid AI Exploration<https://github.com/webmachinelearning/proposals/issues/5> proposal

ℹ️ Open issues and PRs
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-07-wg-agenda.md#%E2%84%B9%EF%B8%8F-open-issues-and-prs>

Discuss open issues and review PRs based on your feedback:

  *   All open issues<https://github.com/webmachinelearning/webnn/issues>
  *   All pull requests<https://github.com/webmachinelearning/webnn/pulls>

A curated shortlist of recently discussed issues:

🏷️ bug<https://github.com/webmachinelearning/webnn/labels/bug>
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-07-wg-agenda.md#%EF%B8%8F-bug>

  *   Synchronously validate input operands/activations webmachinelearning/webnn#572<https://github.com/webmachinelearning/webnn/issues/572>
     *   PR webmachinelearning/webnn#591<https://github.com/webmachinelearning/webnn/pull/591>

🏷️ question<https://github.com/webmachinelearning/webnn/labels/question>
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-07-wg-agenda.md#%EF%B8%8F-question>

  *   Core operator set webmachinelearning/webnn#573<https://github.com/webmachinelearning/webnn/issues/573>
  *   Consider adopting new broadcasting rules webmachinelearning/webnn#590<https://github.com/webmachinelearning/webnn/issues/590>
  *   Apply [EnforceRange] to integer types? webmachinelearning/webnn#562<https://github.com/webmachinelearning/webnn/issues/562>
     *   PR webmachinelearning/webnn#592<https://github.com/webmachinelearning/webnn/pull/592>

🏷️ feature request<https://github.com/webmachinelearning/webnn/labels/feature%20request>
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-07-wg-agenda.md#%EF%B8%8F-feature-request>

  *   Consider using label to allow better error handling for async errors webmachinelearning/webnn#585<https://github.com/webmachinelearning/webnn/issues/585>
  *   Consider throwing TypeError for invalid input webmachinelearning/webnn#583<https://github.com/webmachinelearning/webnn/issues/583>
     *   PR webmachinelearning/webnn#589<https://github.com/webmachinelearning/webnn/pull/589>

🏷️ conventions<https://github.com/webmachinelearning/webnn/labels/conventions>
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-07-wg-agenda.md#%EF%B8%8F-conventions>

  *   Rename inputSize variables as inputRank in algorithms webmachinelearning/webnn#588<https://github.com/webmachinelearning/webnn/issues/588>
  *   Consider alternate styling/linking for method argument definitions webmachinelearning/webnn#574<https://github.com/webmachinelearning/webnn/issues/574>

Please refer to the triage guidance<https://github.com/webmachinelearning/webnn/blob/main/docs/IssueTriage.md> for more context.