WebML WG Teleconference – 21 September 2023 - 14:00-15:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-09-21-wg-agenda.md


WebML WG Teleconference – 21 September 2023 - 14:00-15:00 UTC
See the timezone table ...
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-09-21-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/2023Jun/0000.html

  *   Minutes: https://www.w3.org/2023/09/21-webmachinelearning-minutes.html


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-09-21-wg-agenda.md#agenda>Agenda
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-09-21-wg-agenda.md#%E2%84%B9%EF%B8%8F-update-from-tpac-2023>ℹ️ Update from TPAC 2023

W3C's Web Machine Learning WG did not formally meet at this year's TPAC, but the WG's work received a lot of interest during the hallway track and in other meetings. Anssi will share an update.

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-09-21-wg-agenda.md#%E2%84%B9%EF%B8%8F-webnn-v2-proposed-model-targets>ℹ️ WebNN v2: Proposed model targets

The WG has identified the following as its proposed v2 model targets:

  *   Text-to-image: Stable Diffusion unet/VAE/text encoder
  *   Image segmentation: Segment Everything decoder
  *   Speech-to-text: Whisper Tiny
  *   Text-to-text generation (encoder-decoder): t5 and m2m100
  *   Text-generation (decoder-only): llama

We will discuss any feedback and with no concerns we initiate work on an op breakdown to better understand what is common across these architectures to inform WebNN API v2 priorities.

Please provide your feedback via webmachinelearning/webnn#375<https://github.com/webmachinelearning/webnn/issues/375>

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-09-21-wg-agenda.md#%E2%84%B9%EF%B8%8F-storage-apis-for-caching-large-models>ℹ️ Storage APIs for caching large models

Discussion on general issues related to caching large models, current Storage APIs, specific issues and workarounds for those APIs.

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-09-21-wg-agenda.md#%E2%84%B9%EF%B8%8F-security-considerations>ℹ️ Security considerations

  *   Computation control-flow attack based on weights / constants change
     *    issue: webmachinelearning/webnn#443<https://github.com/webmachinelearning/webnn/issues/443>

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-09-21-wg-agenda.md#%E2%84%B9%EF%B8%8F-new-features>ℹ️ New features

  *   Allow checking whether operators/types are supported for a backend before creating a graph
     *    issue: webmachinelearning/webnn#463<https://github.com/webmachinelearning/webnn/issues/463>

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-09-21-wg-agenda.md#%E2%84%B9%EF%B8%8F-enhancements>ℹ️ Enhancements

  *   split() into sizes not widely supported
     *    issue: webmachinelearning/webnn#392<https://github.com/webmachinelearning/webnn/issues/392>
  *   Clarify the restriction for minValue and maxValue of MLClampOptions
     *    issue: webmachinelearning/webnn#396<https://github.com/webmachinelearning/webnn/issues/396>
  *   Type of parameters should match the input data type
     *    issue: webmachinelearning/webnn#442<https://github.com/webmachinelearning/webnn/issues/442>