Information

AI Model Management
  • Past
  • Confirmed
  • Breakout Sessions

Meeting

Event details

Date:
– Pacific Daylight Time
Status:
Confirmed
Location:
2 Ballroom Level - California A
Participants:
Martin Alvarez-Espinar, Kenji Baheux, Alexander Cooper, Domenic Denicola, Wei Ding, Javier Fernandez, Natasha Gaitonde, Dominique Hazaël-Massieux, Iris Johnson, Gregg Kellogg, Zoltan Kis, Mirja Kühlewind, Sandor Major, Michael McCool, Chunhui Mo, Etienne Noël, Chris Pryor, Anatoly Scherbakov, Elias Selman, David Singer, Austin Sullivan, Bing Wang, Tarek ZIADE
Big meeting:
TPAC 2024 (Calendar)

AI models can be executed on the client web platform and can add significant functionality to web applications. However, they can also be quite large, requiring significant resources to download and store. Download and compilation latencies can potentially impact the user experience.

This breakout will discuss ways in which these issues can be mitigated. Possible topics include the following.

  • Background model download and compilation.
  • Caching strategies, including potential cross-site caching mechanisms with privacy-preserving mitigations
  • Model naming and versioning, allowing for model substitution when useful
  • Access to both downloadable and pre-installed models with a common interface
  • Storage deduplication
  • Model representation independence
  • API independence (e.g. sharing models between WebNN and WebGPU implementations)
  • Offline usage, including interaction with PWAs.
  • Common models are lower privacy risks

Note: this is both an AI topic and a Storage topic. Input from both communities would be useful and is encouraged!

There were some related presentations on this topic in the WebML IG.

See:

  • Repo - Please direct followup there, and to the WebML WG

Agenda

Chairs:
Michael McCool

Description:
AI models can be executed on the client web platform and can add significant functionality to web applications. However, they can also be quite large, requiring significant resources to download and store. Download and compilation latencies can potentially impact the user experience.

This breakout will discuss ways in which these issues can be mitigated. Possible topics include the following.

  • Background model download and compilation.
  • Caching strategies, including potential cross-site caching mechanisms with privacy-preserving mitigations
  • Model naming and versioning, allowing for model substitution when useful
  • Access to both downloadable and pre-installed models with a common interface
  • Storage deduplication
  • Model representation independence
  • API independence (e.g. sharing models between WebNN and WebGPU implementations)
  • Offline usage, including interaction with PWAs.
  • Common models are lower privacy risks

Note: this is both an AI topic and a Storage topic. Input from both communities would be useful and is encouraged!

There were some related presentations on this topic in the WebML IG.

See:

  • Repo - Please direct followup there, and to the WebML WG

Goal(s):
Prioritize issues, discuss highest priority issues, define follow-up actions if possible.

Agenda:

  1. Review list of issues and add or refine any if necessary (5m)
  2. Prioritize issues, identify shortlist for discussion (10m)
  3. Discuss potential solutions to high-priority issues (approx 15m each)
    • Expand explanation of each issue, identify stakeholders
    • Discuss possible resolutions
    • Define followup actions and collaborations

Materials:

Track(s):

  • AI

Minutes

 Read minutes

Export options

Personal Links

Please log in to export this event with all the information you have access to.

Public Links

The following links do not contain any sensitive information and can be shared publicly.

Feedback

Report feedback and issues on GitHub.