arXiv Computation and Language

SGD-KV: Summarization Guided KV Cache Compression

SGD-KV is a head‑aware framework for compressing key‑value caches in large language models. It uses a chunk‑summarization diagnostic task to identify attention heads that specialize in hierarchical information aggregation, allowing the KV cache budget to be allocated based on each head’s summarization score. Experiments on Qwen2.5‑7B‑1M and Qwen3‑32B show state‑of‑the‑art performance on up to 1M‑token contexts while cutting KV cache memory usage by up to 75%.

Hugging Face Trending Papers
Sep 3

SGD-KV: Summarization Guided KV Cache Compression

SGD-KV is a head‑aware framework that compresses key‑value caches in large language models by using a chunk‑summarization diagnostic task to identify attention heads that specialize in hierarchical information aggregation. It prioritizes these heads during compression, achieving state‑of‑the‑art performance on long‑context benchmarks with up to 1M tokens while cutting KV cache memory usage by as much as 75%. Experiments on Qwen2.5‑7B‑1M and Qwen3‑32B confirm that allocating cache budget based on summarization scores yields a superior efficiency‑accuracy trade‑off for long‑context inference.

arXiv AI
Jun 24

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference

arXiv:2606. 24467v1 Announce Type: new Abstract: Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware.

By Xiaolin Lin, Jingcun Wang, Olga Kondrateva, Yiyu Shi, Bing Li, Grace Li Zhang
arXiv AI
Jul 8

Benchmarking KV-Cache Optimizations across Task Quality and System Performance for Long-Context Serving

arXiv:2607. 05399v1 Announce Type: cross Abstract: Large language model serving is increasingly limited by KV-cache growth under long-context workloads, yet existing KV-cache compression techniques are difficult to compare because they were evaluated on different models, tasks, budgets, and serving stacks.

By Nikita Agrawal, Ruben Mayer
arXiv AI
Sep 2

KV Cache Offloading for Context-Intensive Tasks

The paper investigates KV cache offloading for long‑context large language models, focusing on tasks that require extensive information extraction from the prompt. The authors introduce the Text2JSON benchmark, a highly context‑intensive task that demands structured knowledge extraction from raw text, and evaluate modern KV offloading techniques on this benchmark and other similar tasks. Their experiments on Llama 3 and Qwen 3 reveal significant accuracy degradation, attributing it to low‑rank key projection and unreliable landmarks, and propose a simpler strategy that markedly improves performance across multiple LLM families.

By Andrey Bocharnikov, Ivan Ermakov, Denis Kuznedelev, Vyacheslav Zhdanovskiy, Yegor Yershov
arXiv AI
Jun 9

From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs

arXiv:2606. 09508v1 Announce Type: new Abstract: Existing sparse attention and KV cache compression methods for long-context LLM inference typically apply fixed sparsity patterns or uniform budgets across all attention heads, overlooking the substantial variation in attention behavior among heads and contexts.

By Zhanchao Xu, Haoyang Li, Qingfa Xiao, Fei Teng, Chen Jason Zhang, Lei Chen, Qing Li