Block Ffn Sparse Mixture Experts

Deploy efficient MoE models on resource-constrained edge devices by learning chunk-level activation sparsity that achieves 3.67× speedup. Use when you need to compress LLMs for on-device inference while maintaining reasoning quality and supporting speculative decoding acceleration.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit ba9cc41b30

Frequently asked questions

npx get-skill add adu2021/block-ffn-sparse-mixture-experts