DeepSeek-V4 长上下文服务系统 RedKnot-MLA 发布
RedKnot-MLA: Multi-Head Offline-Online Reuse for DeepSeek-V4 Long-Context Serving
DeepSeek 推出了 RedKnot-MLA 系统，能显著提升长上下文服务的速度和效率，在多个基准测试中表现优异。
DeepSeek-V4 推出 RedKnot-MLA 系统，采用多头部离线-在线重用技术。该系统在 256K 上下文长度下，F1 分数提升 3.24 个百分点，EM 分数提升 4.16 个百分点。DeepSeek-V4-Flash 使用 37 个可重用层，达到 75.29% 的逻辑头部行上限，Pro-0813 配置达到 78.89%。
RedKnot-MLA: Multi-Head Offline-Online Reuse for DeepSeek-V4 Long-Context Serving
Multi-head latent attention (MLA) exposes many logical query heads through one packed latent KV stream. This representation is memory efficient, but it removes the physical per-head cache boundary assumed by conventional head-wise reuse. We present our system, a DeepSeek-V4 realization of RedKnot's head-aware reuse principle. Each immutable document is processed offline at canonical position zero; certified Local-head contributions are retained as MLA-Off. At serving time, query-side RoPE relocation restores the document's request position, a small Global-head set and protected Local token rows are recomputed as MLA-Online, and the two paths are merged before a single shared output projection. The packed MLA latent is never split. DeepSeek-V4-Flash uses 37 reusable layers and a 56/8 Local/Global partition, giving a 75.29% analytic logical head-row ceiling; the Pro-0813 profile uses 55 layers and 112/16 heads, giving 78.89%. Frozen Flash operating points show hot-artifact TTFT speedups of 2.02-3.84x. At 256K, the archived three-dataset study reports an aggregate F1 change of +3.24 percentage points, an EM change of +4.16 points, and a 78.7-79.5% analytic major-operator arithmetic saving, while one dataset decreases by 2.81 F1 points. A separate author-reported 256K hot-artifact QPS measurement is approximately 2.0x; because its raw concurrency trace is not included in this bundle, we mark it as preliminary rather than archived evidence. We describe the factorization, position repair, token-row closure, sparse-MoE support, TP8 integration, and the measurement boundaries needed to interpret these results.
