Jeadie / edge-inference

Cloudflare for the AI age

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

edge

AI search on the edge

Issues I am tracking:

TODO List

Search/storage size

  • Select basic rust ANN library and/or server: Using Qdrant for now
    • Bundle and run locally
  • Check if we need to Webassembly run on Cloudflare workers
  • Get Cloudflare account
  • Possible storage compression
  • Possible edge storage for large fields

Model Size

  • Best way to run model on edge
  • How to make model smaller
    • Transformer size
    • Sparsity reduction

Others

  • Ideal beta customers
  • Auth

About

Cloudflare for the AI age


Languages

Language:Rust 100.0%