Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Spaces:
HOLOGRAMTECH
/
bonsai-kappa-stream
Running

App Files Files Community
bonsai-kappa-stream / q /core
43.5 kB
Ctrl+K
Ctrl+K
  • 4 contributors
History: 2 commits
humuhumu33
Claude Fable 5
Keep multi-turn conversations fast: snapshot the conversation's KV before the follow-up-suggestion pass evicts it, and restore it before the next turn so only the new turn prefills instead of re-processing the whole thread. Measured 20x faster re-prefill on a 459-token thread (12s to 0.6s, same GPU back-to-back), byte-identical by determinism, gated to long threads on capable desktops.
a593567 4 months ago
  • engine.js
    22.7 kB
    Keep multi-turn conversations fast: snapshot the conversation's KV before the follow-up-suggestion pass evicts it, and restore it before the next turn so only the new turn prefills instead of re-processing the whole thread. Measured 20x faster re-prefill on a 459-token thread (12s to 0.6s, same GPU back-to-back), byte-identical by determinism, gated to long threads on capable desktops. 4 months ago
  • holo-stream-load.mjs
    13.1 kB
    Bonsai kappa-stream: self-contained showcase (app + engine closure) 4 months ago
  • kappa.js
    5.07 kB
    Bonsai kappa-stream: self-contained showcase (app + engine closure) 4 months ago
  • kv-commons.mjs
    2.66 kB
    Bonsai kappa-stream: self-contained showcase (app + engine closure) 4 months ago