RIFT introduces selection‑based KV cache compression strategies that balance prefill information with recently generated tokens to mitigate decode staleness in speculative decoding. By refreshing the KV cache selection during token generation and employing an adaptive refresh strategy, RIFT improves drafter quality while managing decode latency. A compressibility‑driven drafter training phase further enhances performance, enabling Qwen3.5‑4B to retain over 98% of its full‑cache acceptance length within an 8K‑token KV cache budget on long‑context inputs.
By Dor Tsur, Maor Ashkenazi, Maximilian Golub, Peter Hicks, Yaniv Galron, Talor Abramovich, Yoav Miron, Tiyasa Mitra, Bita Darvish Rouhani, Ran Zilberstein
arXiv:2609.37988v1 Announce Type: new
Abstract: As the context size of text processed with an LLM grows, the size of KV caches can outstrip the memory allocated for the original model weights. This i...
By Joao Monteiro, Louis B\'ethune, Anastasiia Filippova, Sonia Laguna, David Grangier, Marco Cuturi
The paper addresses the challenge of long input contexts in Retrieval-Augmented Generation (RAG) systems, where concatenating many retrieved chunks increases prefill workload and time to first token (TTFT). It proposes a dual strategy: fine‑tuning the model to be aware of KV cache concatenation and selectively recomputing only part of the KV caches. Experiments on the RULER benchmark show that for a 124k‑token input, this combined method boosts the RULER score by 9.7 points over a baseline that recomputes caches only, while cutting TTFT by 80% compared with full attention.
By Fumihiko Tachibana, Daisuke Miyashita, Jun Deguchi
arXiv:2609.24197v1 Announce Type: new
Abstract: Speculative decoding losslessly accelerates large language model inference by having a lightweight draft model predict future tokens for verification b...
By Weifan Jiang, Krishna Teja Chitty-Venkata, Megan Flynn, Reed Meyerson, Zhenting Qi, Tianyu Wu, Eldar Kurtic, Minlan Yu, Alexandre Marques
arXiv:2606. 00144v1 Announce Type: cross Abstract: Speculative decoding speeds up autoregressive decoding by using a drafter to propose multiple tokens that a verifier validates in parallel.
By Liang He, Jingbo Wen, Qishi Zhan, Yixiong Chen, Kangning Cui, Qizhen Lan, Xilu Wang
arXiv:2608.30252v1 Announce Type: new
Abstract: Long-context LLM applications such as document summarization and multi-turn agents require generation from prefixes spanning tens of thousands of token...
By Tong Yuan, Chengxi Liao, Zeyi Wen
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. Sp...
arXiv:2607. 06519v1 Announce Type: new Abstract: Long-context LLM inference is increasingly limited by the memory and bandwidth cost of KV caches, yet aggressive compression can remove the layer-specific evidence needed for retrieval and multi-step reasoning.
By Anna C\'ordoba, Adam Puente Tercero, Nerea Angulo Hijo, Mar Linares Tercero, Julia Barrientos, Ainhoa Miranda, Jes\'us Olivera
arXiv:2609.07966v1 Announce Type: new
Abstract: Key--value (KV) cache compression is an effective way to reduce the memory overhead of large language model (LLM) inference, particularly for long-cont...
By Michael Wang, Keith Li, Roozbeh Bostandoost
arXiv:2608. 01247v1 Announce Type: cross Abstract: Query-agnostic KV cache eviction compresses a context once and reuses the resulting cache for arbitrary future queries, but performance can collapse under tight budgets.
By Changwoo Baek, Seungjun Shin, Kyeongbo Kong
arXiv:2606. 15157v1 Announce Type: cross Abstract: KV cache compression is essential for reducing the memory cost of long-context large language model inference.
By Chao Fei, Panos Kalnis
Query-agnostic KV cache eviction compresses a context once and reuses the resulting cache for arbitrary future queries, but performance can collapse under tight budgets. Existing methods primarily improve which original KV pairs are retained.