RedKnot-MLA: Multi-Head Offline-Online Reuse for DeepSeek-V4 Long-Context Serving

arXiv:2609.07008 · cs.AI · Submitted 2026-09-07 · Read on arXiv

cs.AI

Submitted: 2026-09-07

Updated: 2026-09-28

Code: https://github.com/rednote-machine-learning/RedKnot

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Trace — 6× in this paper · explained in 2 episodes
• RAG — 2× in this paper · explained in 3 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• KV cache reuse — 1× in this paper · explained in 2 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
• DeepSeek-V3 Technical Report
• RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention
• HYPIC: Accelerating Hybrid-Attention LLM Serving with Position-Independent Caching

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection