block-ffn-sparse-mixture-experts

【部署与运维】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.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准