lookaheadkv-predictive-cache-eviction

【效率与协作】Evict unnecessary KV cache entries using trainable lookahead tokens and LoRA modules that predict token importance without drafting responses. Achieve 14.5× speedup over draft-based methods with 2% eviction overhead.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准