Skip to content

MoE on-demand expert loading from OPFS/IndexedDB #387

Description

@sauravpanda

Context

In MoE models (e.g., DeepSeek-R1), expert parameters are 97.45% of total but only 3.13% activated per token. OD-MoE (Dec 2025) achieves 99.94% expert prediction accuracy with 1/3 GPU memory.

Proposal

  • Store MoE expert weights in OPFS (3-4x faster I/O than IndexedDB)
  • Predict which experts are needed 1-2 layers ahead
  • Load only active experts into GPU memory on-demand
  • Run much larger models (8x22B Mixtral) by only keeping ~2 experts resident
  • MoLE (ICML 2025): pre-computed lookup tables for experts — zero computation for expert layers

Impact

  • Run 10B+ effective-parameter MoE models in browser with <2GB active memory
  • First browser engine with native MoE support

References

  • OD-MoE — on-demand expert loading
  • FlashMoE — ML-based cache replacement
  • MoLE — lookup table experts

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    browserBrowser/WASM specificinnovationNovel/differentiated features

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions