lychee-decode-sparse-kv-sharing

【开发与工程】Classify attention heads into retrieval (full attention) and sparse (token-selected) roles using HardKuma distribution for differentiable discrete optimization. Sparse heads reuse KV pairs from retrieval heads, reducing cache by 90% while maintaining quality through joint training.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准