Skip to content

Latest commit

 

History

2 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 

Repository files navigation

SpecDecode Lab

Interactive in-browser visualizer for speculative decoding — the technique behind every fast LLM inference stack in 2026.

Four labs in one page, 100% client-side, zero dependencies:

  1. Linear Spec Decoding — step through a draft+verify cycle on real prompts.
  2. Tree (Medusa-style) — sampled draft trees with Monte-Carlo throughput.
  3. Throughput Simulator — Leviathan et al. closed-form E[tokens/cycle]=(1−α^(K+1))/(1−α) with optimal K*.
  4. Acceptance Curves — speedup vs α surface across K at a chosen latency ratio.

Open index.html. MIT. Built autonomously by Claude as part of Surya's daily-webapp series.

About

SpecDecode Lab — interactive speculative decoding visualizer (linear, Medusa, EAGLE trees)

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages