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

• URL: http://arxiv.org/abs/2608.30252v1
• Date: Mon, 31 Aug 2026 05:03:30 GMT
• Title: Strong Drafts Need Compact Memories: Long-Context Speculative Decoding with Compressed KV Cache
• Abstract summary: Long-context document summarization applications require generation from prefixes spanning tens of thousands of tokens.<n> Speculative decoding (SD) reduces latency without changing model outputs, but its speedup depends on both accepted draft tokens and draft-step latency.<n>We introduce memory-augmented drafting for long-context SD, equipping a strong independent draft with compressed draft-side KV memory.
• Score: 9.619930280504603
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• End-to-End Context Compression at Scale [81.70601323130997]
  Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length.<n>Recent techniques to compress the KV cache fall short: they either degrade model quality substantially or require considerable time and compute to compress a single long prompt.<n>Existing approaches are not competitive with KV cache compression on the accuracy-efficiency frontier.
  arXiv  Detail & Related papers  (2026-06-08T15:43:16Z)
• Kwai Summary Attention Technical Report [69.40814939510126]
  Long-context ability, has become one of the most important direction of next-generation Large Language Models.<n>Standard softmax attention exhibits quadratic time complexity with respect to sequence length.<n>We propose Kwai Summary Attention (KSA), a novel attention mechanism that reduces sequence modeling cost by compressing historical contexts.
  arXiv  Detail & Related papers  (2026-04-27T12:59:53Z)
• ARKV: Adaptive and Resource-Efficient KV Cache Management under Limited Memory Budget for Long-Context Inference in LLMs [1.1267872663780352]
  Large Language Models (LLMs) are increasingly deployed in scenarios demanding ultra-long context reasoning.<n>Existing memory reduction techniques, including eviction and quantization, often rely on static cache.<n>We propose ARKV, a lightweight and adaptive framework that dynamically allocates precision levels to cached tokens.
  arXiv  Detail & Related papers  (2026-02-19T16:24:08Z)
• DeltaKV: Residual-Based KV Cache Compression via Long-Range Similarity [50.52392445266824]
  We propose a residual-based KV cache compression framework motivated by long-range inter-token similarity and highly shared latent components in KV representations.<n>Instead of discarding tokens, DeltaKV encodes semantic residuals relative to retrieved historical references, preserving fidelity while substantially reducing storage.<n>Experiments show that DeltaKV reduces KV cache memory to 29% of the original while maintaining near-lossless accuracy on LongBench, SCBench, and AIME.
  arXiv  Detail & Related papers  (2026-02-08T15:14:36Z)
• OjaKV: Context-Aware Online Low-Rank KV Cache Compression with Oja's Rule [54.37983890753086]
  We introduce OjaKV, a framework that integrates a strategic hybrid storage policy with online subspace adaptation.<n>OjaKV preserves crucial first and most recent tokens in full-rank, maintaining high-fidelity anchors for attention.<n>It applies low-rank compression by incrementally adapting the projection basis using Oja's algorithm for online principal component analysis.
  arXiv  Detail & Related papers  (2025-09-25T21:42:27Z)
• Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs? [79.58770714228983]
  Language models handle increasingly long contexts for tasks such as book summarization.<n>This leads to growing memory costs for the key-value ( KV) cache.<n>Many prior works have proposed ways of discarding KVs from memory, but their approaches are tailored to favorable settings.<n>We propose the * KV footprint* as a unified metric, which accounts for both the amount of KV entries stored and their lifespan in memory.
  arXiv  Detail & Related papers  (2025-06-20T16:21:12Z)
• SPIRe: Boosting LLM Inference Throughput with Speculative Decoding [5.738617783286307]
  Speculative decoding (SD) has been shown to reduce the latency of autoregressive decoding (AD) by 2-3x for small batch sizes.<n>Recent work shows that SD can accelerate decoding with large batch sizes too if the context is sufficiently long and the draft model's KV cache is sparse.
  arXiv  Detail & Related papers  (2025-04-08T20:39:20Z)
• LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification [42.54363549922909]
  LongSpec is a framework that addresses the challenges of efficient inference over long contexts.<n>LongSpec achieves up to a 3.26x speedup over strong Flash Attention baselines.<n>The code is available at https://github.com/sail-sg/LongSpec.
  arXiv  Detail & Related papers  (2025-02-24T18:53:31Z)
• QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache [67.84112700032007]
  Large Language Models (LLMs) are increasingly being deployed on edge devices for long-context settings.<n>In these scenarios, the Key-Value ( KV) cache is the primary bottleneck in terms of both GPU memory and latency.<n>We propose a novel self-speculative decoding framework, QuantSpec, where the draft model shares the architecture of the target model but employs a hierarchical 4-bit quantized KV cache and 4-bit quantized weights for acceleration.
  arXiv  Detail & Related papers  (2025-02-05T20:43:48Z)
• FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation [14.33163594016033]
  Large language models (LLMs) require substantial prefill computation and key-value ( KV) cache.<n>Recent works that compress KV caches with prefill acceleration reduce this cost but inadvertently tie the prefill compute reduction to the decoding KV budget.<n>FastKV is a KV cache compression framework designed to reduce latency in both prefill and decoding by leveraging the stabilization of token importance in later layers.
  arXiv  Detail & Related papers  (2025-02-03T05:25:09Z)
• MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding [12.74265334789358]
  We show that speculative decoding can achieve speedup even for a high throughput inference regime for moderate to long sequences.<n>We propose a theoretical model to select the optimal drafting strategy for maximum speedup.<n>For moderate to long sequences, we demonstrate up to 2.51x speedup for Llama3.1-8B when serving batch sizes ranging from 32 to 256.
  arXiv  Detail & Related papers  (2024-08-20T17:57:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.