DualDecoder: Accelerate Long Context LLM Inference by Predictive Prefetch

DualDecoder addresses the memory bottleneck in long-context LLM inference caused by the growing KV cache. It predicts critical KV entries for the next token from the preceding speculated token, enabling proactive prefetching from host memory. Experiments show up to 2.62× throughput improvement over state-of-the-art systems without degrading latency or model quality. This matters because it eliminates GPU memory overhead from auxiliary states, making high-concurrency long-context inference more efficient for agentic applications.