Spaces:
Running
Running
metadata
title: LLM Inference Pipeline Simulator
emoji: π
colorFrom: gray
colorTo: blue
sdk: static
pinned: false
LLM Inference β Pipeline Simulator
Interactive visualization of the LLM inference pipeline (prefill, decode, KV cache). From EXD Episode 3 β Inference Benchmarking.
Built with vanilla HTML/CSS/JS. Zero dependencies.
πΊ Watch the episode | π» GitHub