Interface-Aware KV Cache Quantization for Dense On-Chip NVM in Long-Context LLM Decoding

• URL: http://arxiv.org/abs/2609.05764v1
• Date: Fri, 04 Sep 2026 22:58:21 GMT
• Title: Interface-Aware KV Cache Quantization for Dense On-Chip NVM in Long-Context LLM Decoding
• Abstract summary: Key-value (KV) cache is the dominant memory bottleneck in long-context large language model (LLM) decoding.<n>Existing KV quantization methods were designed for GPU-style memory systems.<n>This paper examines what these structures cost when the KV cache resides in NVM behind fixed-range converters.
• Score: 5.984068900226547
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The key-value (KV) cache is the dominant memory bottleneck in long-context large language model (LLM) decoding: every step reads it entirely, so decoding is memory-bandwidth bound. Holding a quantized KV cache in dense on-chip non-volatile memory (NVM) removes the off-chip transfer. Existing KV quantization methods, however, were designed for GPU-style memory systems: KIVI attaches per-group metadata, adding about 25% to the stored KV cache; KVQuant keeps sparse full-precision outliers that a dense array cannot hold in place. This paper examines what these structures cost when the KV cache resides in NVM behind fixed-range converters, and designs a quantization scheme matched to that interface. The architecture stores the quantized KV cache in dense on-chip NVM, uses a small static analog crossbar only for the fixed rotation, and keeps attention in on-chip digital logic. A randomized rotation and per-vector normalization give every coordinate the same range, so one fixed codebook for keys and one for values, each shared across all tokens of the corresponding tensor type, serve the entire KV cache. The codebook thresholds are programmed once as the read converter's reference levels, enabling fixed-range digitization with no per-token converter reconfiguration. Dequantization is a sixteen-entry lookup and one norm multiply; the only per-vector metadata is one scalar, about 3%. Across models from 3B to 14B and contexts to 32k tokens, the four-bit KV cache maintains accuracy under storage and crossbar noise simulated at realistic device levels. KIVI and KVQuant remain more accurate in software; the advantage of our format lies at the memory interface: 3.1-3.6x lower KV read energy than both mapped to the same NVM, and 8x lower metadata overhead than KIVI. The contribution is a KV quantization co-designed with the NVM memory interface rather than a new accuracy record.

Related papers

• Fractal KV-Cache Archives: Lossless Symbolic Storage with In-Place Retrieval for Long-Context LLM Inference [0.0]
  Key-value ( KV) cache dominates the memory cost of long-context autoregressive inference.<n>We study how to store the resulting symbol stream once a position's KV state has been quantized to codebook indices.<n>A family of contractive iterated-map codes that serialize a symbol sequence into a sequence of low-dimensional real vectors is revisited.
  arXiv  Detail & Related papers  (2026-07-08T08:37:49Z)
• KV-CAR: KV Cache Compression using Autoencoders and KV Reuse in Large Language Models [3.5171501100868876]
  The KV cache grows with sequence length and embedding dimension, often exceeding the memory footprint of the model itself.<n>We present KV CAR, a unified and agnostic architecture framework that significantly reduces KV cache storage while maintaining model fidelity.<n> Evaluations on GPT 2 and TinyLLaMA models across Wikitext, C4, PIQA, and Winogrande datasets demonstrate that KV CAR achieves up to 47.85 percent KV cache memory reduction.
  arXiv  Detail & Related papers  (2025-12-07T08:40:52Z)
• KV Cache Transform Coding for Compact Storage in LLM Inference [2.20003167536462]
  We present KVTC, a lightweight transform coder that compresses KV caches for compact on- GPU and off- GPU storage.<n>By exploiting redundancies in KV caches, KVTC achieves up to 20$times$ compression while maintaining reasoning and long-context accuracy.<n>We test KVTC with Llama 3, Mistral NeMo, and R1-Qwen 2.5 models across benchmarks including AIME25, LiveCodeBench, GSM8K, MMLU, Qasper, RULER, and MATH-500.
  arXiv  Detail & Related papers  (2025-11-03T18:20:35Z)
• CommVQ: Commutative Vector Quantization for KV Cache Compression [50.37946553931796]
  We propose Commutative Vector Quantization (CommVQ) to significantly reduce memory usage for long-context LLM inference.<n>We first introduce additive quantization with a lightweight encoder and codebook to compress the KV cache.<n>Our approach achieves high accuracy with additive quantization and low overhead via the RoPE-commutative codebook.
  arXiv  Detail & Related papers  (2025-06-23T17:50:11Z)
• 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)
• KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing [58.29726147780976]
  We propose a plug-and-play method called textit KVSharer, which shares the KV cache between layers to achieve layer-wise compression. Experiments show that textit KVSharer can reduce KV cache computation by 30%, thereby lowering memory consumption. We verify that textit KVSharer is compatible with existing intra-layer KV cache compression methods, and combining both can further save memory.
  arXiv  Detail & Related papers  (2024-10-24T08:06:41Z)
• LoCoCo: Dropping In Convolutions for Long Context Compression [77.26610232994508]
  This paper presents a novel approach, Dropping In Convolutions for Long Context Compression (LoCoCo) LoCoCo employs only a fixed-size Key-Value ( KV) cache, and can enhance efficiency in both inference and fine-tuning stages.
  arXiv  Detail & Related papers  (2024-06-08T01:35:11Z)
• QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead [10.067037913589175]
  Serving LLMs requires substantial memory due to the storage requirements of Key-Value embeddings in the KV cache. Traditional quantization methods face significant memory overhead due to the need to store quantization constants. We introduce QJL, a new quantization approach that consists of a Johnson-Lindenstrauss transform followed by sign-bit quantization.
  arXiv  Detail & Related papers  (2024-06-05T17:42:05Z)
• KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache [67.9776980972508]
  We develop a tuning-free 2bit KV cache quantization algorithm named KIVI. KIVI can enable Llama, Falcon, and Mistral models to maintain almost the same quality while using $mathbf2.6times$ less peak memory.
  arXiv  Detail & Related papers  (2024-02-05T06:06:47Z)
• KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization [67.74400574357472]
  LLMs are seeing growing use for applications which require large context windows, and with these large context windows KV cache activations surface as the dominant contributor to memory consumption during inference.<n> Quantization is a promising approach for compressing KV cache activations; however, existing solutions fail to represent activations accurately in sub-4-bit precision.<n>Our work, KVQuant, facilitates low precision KV cache quantization by incorporating several novel methods.
  arXiv  Detail & Related papers  (2024-01-31T18:58:14Z)

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.