Apd Adaptive Parallel Decoding

Accelerate diffusion language model inference by dynamically adjusting parallel tokens per step using a small auxiliary autoregressive model, achieving substantial throughput gains.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 2ce4eb4de4

Frequently asked questions

npx get-skill add adu2021/apd-adaptive-parallel-decoding