The paper introduces VFold, a symmetry‑aware strategy for merging value caches across layers in large language models to reduce memory usage during decoding. It avoids the performance penalties and architectural changes typical of other compression methods, and can be combined with high‑ratio quantization or key cache pruning to achieve higher compression ratios. The authors demonstrate that a significant portion of the value cache is underutilized, providing a straightforward path to scaling context windows within memory limits.
By Neha Verma, Sungwon Kim, Kenton Murray, Kevin Duh
MultiAlloc is a profiling‑guided framework that allocates limited quantization resources between layer‑wise precision enhancement and token‑wise preservation for KV cache quantization in large language models. By using lightweight offline profiling to assess layer sensitivity and token importance, it automatically derives an effective precision allocation strategy that satisfies a fixed memory budget without online search. Experiments on reasoning and long‑context benchmarks show that MultiAlloc consistently outperforms existing layer‑wise, token‑wise, and multi‑granularity quantization methods across models such as Mistral, Llama, DeepSeek‑Qwen, and QwQ.
arXiv:2608. 02901v1 Announce Type: new Abstract: The key-value (KV) cache is the primary memory bottleneck in long-context LLM inference.
By Malik Khalaf, Yara Shamshoum, Nitzan Hodos, Yuval Sieradzki, Assaf Schuster
arXiv:2610.03027v1 Announce Type: cross
Abstract: The key-value (KV) cache becomes a major memory bottleneck in long-context LLM inference, placing substantial pressure on memory capacity and bandwid...
By Minsoo Cheong, Donghyun Son, Sungjoo Yoo
arXiv:2609.39329v1 Announce Type: new
Abstract: Long-context inference with Large Language Models (LLMs) is bottlenecked by the linearly growing memory of the key-value (KV) cache. Existing compressi...
By Chanryeol Lee, Chanhyuk Lee, Yeonwoo Choi, Donggyun Kim, Seunghoon Hong
arXiv:2608.23843v1 Announce Type: new
Abstract: Long-context inference in large language models (LLMs) is increasingly limited by the memory required for the key-value (KV) cache. KV cache compressio...
By Zizhong Wang, Jieying Wang, Zhao Zhang, Jiajia Li
arXiv:2607. 01237v1 Announce Type: cross Abstract: Reasoning language models often generate long chain-of-thought (CoT), which accumulates a massive KV cache during the decoding phase and incurs high decoding latency and limited throughput.
By Shen Han, Yuyang Wu
arXiv:2610.15384v1 Announce Type: cross
Abstract: Compressing the key-value (KV) cache is essential for serving long-context large language models (LLMs) under memory constraints. While current scala...
By Sasho Nedelkoski, Alexander Acker, Soeren Becker, Dominik Scheinert, Odej Kao
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
Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length. 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.
arXiv:2608.21362v1 Announce Type: new
Abstract: Transformer-based large language models (LLMs) incur high prefill latency because key-value (KV) tensors must be recomputed for each request. Existing...
By Srihari Unnikrishnan
arXiv:2607. 00760v1 Announce Type: new Abstract: Long-context LLM services now sustain prompts with hundreds of thousands to millions of tokens, making the key-value (KV) cache a first-order serving cost.
By Sheng Qiang, Ruiwei Chen, Yinpeng Wu, Jinyu Gu, Zhichao Hua, Yubin Xia, Binyu Zang, Haibo Chen