arXiv:2607. 09683v1 Announce Type: cross Abstract: This study systematically compares Turbo-Quant and SpectralQuant KV-cache compression, evaluating non-dominated schemes, including WHT rotation with Beta Lloyd-Max and QJL, through a statistical validation methodology that separates systematic codec differences from implementation variance.
arXiv:2608. 09412v1 Announce Type: new Abstract: KV-cache compression reduces long-context memory, but aggregate task scores reveal neither which correct executions fail nor why.
arXiv:2608. 07915v1 Announce Type: new Abstract: Large language models (LLMs) increasingly read long inputs in the agentic era, from whole documents and codebases to conversations across many turns.
arXiv:2607. 20538v1 Announce Type: cross Abstract: Long-context Transformer inference increasingly relies on KV-cache compression or quantization.
arXiv:2609.24298v1 Announce Type: new Abstract: What limits KV-cache compression at extreme bit-rates? We argue that it is not the choice of compression scheme, but how its budget is allocated across...
arXiv:2606. 15157v1 Announce Type: cross Abstract: KV cache compression is essential for reducing the memory cost of long-context large language model inference.
arXiv:2604.11501v2 Announce Type: replace-cross Abstract: Rank reduction discards dimensions; quantization keeps them at lower precision. Comparing the two requires a choice of what compression shoul...
arXiv:2607. 01065v1 Announce Type: new Abstract: The deployment of Large Language Models (LLMs) with extended context windows is increasingly constrained by the linear growth of Key-Value (KV) cache memory.
arXiv:2607. 01520v1 Announce Type: new Abstract: Transformer inference on long sequences is expensive because softmax attention repeatedly reads from a large KV cache.
arXiv:2608. 08684v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by KV cache memory, yet distributing a limited cache budget across layers remains challenging.
The paper investigates how to recover language model quality lost when using low‑bit key–value caches for autoregressive decoding. By keeping the quantizer fixed and distilling the full‑precision cache behavior into low‑rank Q/K/V projection updates, the authors demonstrate that 4‑bit affine‑cache adapters recover roughly 54 % of the perplexity gap on TinyLlama‑1.1B and 76 % on Gemma‑4‑12B, while preserving most long‑context retrieval. Even a 2‑bit rank–token sweep can dramatically reduce TinyLlama’s perplexity, though it only partially restores retrieval performance.
arXiv:2606. 03458v1 Announce Type: new Abstract: Test-time scaling is a powerful approach to obtain better reasoning in large language models, but it becomes memory-bottlenecked during long-horizon decoding, as the KV-cache grows.
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.