Strong Drafts Need Compact Memories: Long-Context Speculative Decoding with Compressed KV Cache

2026-08-31

AI Summary

研究解决了长文本生成中的解码延迟问题，通过使用压缩KV缓存的推测解码方法，在保持模型输出不变的情况下显著提高了生成速度。

Abstract

Long-context LLM applications such as document summarization and multi-turn agents require generation from prefixes spanning tens of thousands of tokens, making decoding latency a major bottleneck. Speculative decoding (SD) reduces latency without changing model outputs, but its speedup depends on both accepted draft tokens and draft-step latency: Lightweight drafts are fast but lack the capacity to capture long-range dependencies, whereas strong independent drafts recover acceptance but incur growing KV-access cost at long prefixes. We introduce memory-augmented drafting for long-context SD, equipping a strong independent draft with compressed draft-side KV memory: A lightweight adaptor constructs and incrementally updates this memory to retain distant information and exact recent context. The target verifier retains its full KV cache and applies the standard accept/reject rule, preserving SD's lossless guarantee. Experiments on Llama~3.1-8B and 70B targets at prefix lengths up to 32K show that our method reduces draft-side memory by over 70%. It achieves speedups of up to 2.08x and 3.33x , respectively, over autoregressive decoding.

Problem

• long-context
• speculative decoding
• KV cache
• decoding latency

Innovation

• memory-augmented drafting
• compressed KV memory
• speculative decoding
• long-context generation