AI推理不再死记硬背：只留关键记忆，长文本提速90%
大模型处理超长文本时，GPU内存会被历史对话的缓存撑爆。这篇论文反其道而行：让模型学会预判接下来需要哪些历史信息，只把关键片段留在显存里，其余扔掉。他们训练了一个独立的“记忆索引器”，像搜索引擎一样提前筛选出相关缓存，在500K超长文本下，显存占用减少90%以上，准确率反而微升。这不是你明天能用的功能，但它指向一个趋势：未来的AI不会被动记住一切，而是主动选择该记什么。
📄 原文摘要(英文)
Conventional LLMs keep the full KV cache loaded during decoding, causing a severe GPU memory bottleneck for ultra-long context serving. In this report, we propose Lookahead Sparse Attention (LSA), a novel inference paradigm powered by a Neural Memory Indexer built upon the DeepSeek-V4 architecture. Rather than passively attending to all historical tokens, LSA proactively predicts future context demands and preserves only the query-critical KV chunks in the GPU memory. Crucially, we instantiate this architecture via a backbone-free decoupled training strategy. By formulating the indexer as a standard dual-encoder architecture, we train it independently using standard retrieval training frameworks without ever loading the massive backbone model into GPU memory. We demonstrate that this "less is more" paradigm significantly maximizes serving efficiency while acting as an effective attention denoiser in tasks that rely on long-term global memory. Across primary long-context evaluation suites (e.g., LongBench-v2, LongMemEval, and RULER), FM-DS-V4 compresses the average physical KV cache footprint down to merely 13.5% of the full-context baseline, while consistently preserving or slightly elevating downstream accuracy (+0.6% absolute margin on average). Crucially, at extreme 500K scales, FlashMemory suppresses the physical KV cache overhead by over 90% without destabilizing the backbone's core reasoning capacities.