Quantization Dominates Rank Reduction for KV-Cache Compression

• URL: http://arxiv.org/abs/2604.11501v1
• Date: Mon, 13 Apr 2026 14:06:18 GMT
• Title: Quantization Dominates Rank Reduction for KV-Cache Compression
• Abstract summary: quantization consistently outperforms rank reduction by 4-364 PPL depending on model and compression level.<n>We formalize this via a result showing projection damage exceeds quantization damage by 3 x 2 (2b) per direction under the softmax Fisher metric.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We compare two strategies for compressing the KV cache in transformer inference: rank reduction (discard dimensions) and quantization (keep all dimensions, reduce precision). At matched storage budgets across five models (124M-14B, MHA and GQA), we find that quantization consistently outperforms rank reduction by 4-364 PPL depending on model and compression level. The gap persists even when rank reduction is combined with quantization in hybrid baselines, and it grows with GQA aggressiveness. On LAMBADA, INT4 matches FP16 accuracy (+0.23 PPL on Mistral 7B, +0.58 on GPT-2) while rank-32 at identical storage collapses to 0.4%. We trace this gap to a structural asymmetry: under softmax attention routing, removing a dimension can flip which token is attended (a discrete failure), while quantization noise is bounded and typically preserves score ordering. We formalize this via a perturbation result showing projection damage exceeds quantization damage by 3 x 2^(2b) per direction under the softmax Fisher metric. A basis ablation confirms the finding is basis-independent (spread <0.4 PPL), establishing that the advantage comes from preserving dimensions, not from a better coordinate system. Joint K+V INT4 quantization achieves 75% total KV reduction at only +0.18 PPL on Mistral 7B.

Related papers

• Steering Under Compression: Dose-Response, Capability Cost, and Failure Asymmetry in Quantized LLMs [0.0]
  Inference-time steering enables behavioral control of large language models without parameter modification.<n>Post-training quantization reduces memory and compute costs for deployment.<n>We systematically study activation steering under weight-only quantization.
  arXiv  Detail & Related papers  (2026-09-06T08:41:42Z)
• SemKV: Semantic Mixed-Precision KV Cache Quantization Guided by the Quality Cliff for Long-Context LLM Inference [3.2938220347051175]
  We show that uniform KV quantization on a fractional-bit grid does not degrade gracefully.<n>We show that replacing the affine base with a distortion-optimized quantizer (TurboQuant-MSE) prunes the cliff in every protocol tested.
  arXiv  Detail & Related papers  (2026-08-28T22:19:47Z)
• LegoLM: Structured Weight Sharing for Large Language Models [0.0]
  We present LegoLM, a structured weight-sharing compression framework for large language models.<n>LegoLM resolves two failure modes: distributional mismatch and outlier dominance.<n>Across GPT-2 small (124M) and Mistral-7B, LegoLM achieves +0.03% PPL degradation at 4.41X compression on Mistral-7B.
  arXiv  Detail & Related papers  (2026-08-09T11:51:14Z)
• Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution [3.6704226968275253]
  We show gradient-based methods that achieve meaningful forgetting lose it under compression, while methods that survive quantization barely change the model.<n>We present MANSU, which resolves both modes by combining causal circuit attribution to isolate the minimal forget-set subgraph.<n>We additionally introduce Circuit Attribution Divergence (CAD), a mechanistic verification metric distinguishing structural erasure from behavioral suppression.
  arXiv  Detail & Related papers  (2026-05-14T17:44:10Z)
• Normalized Architectures are Natively 4-Bit [49.13186675123547]
  nGPT, an architecture that constrains weights and hidden representations to the unit hypersphere, is inherently more robust to low-precision arithmetic.<n>We validate this approach on both a 1.2B dense model and hybrid (Mamba-Transformer) MoE models of up to 3B/30B parameters.
  arXiv  Detail & Related papers  (2026-05-07T11:54:07Z)
• Towards Joint Quantization and Token Pruning of Vision-Language Models [53.978753457744055]
  Token pruning and low-bit quantization are complementary for reducing inference costs.<n>We present a collaborative quantization-and-pruning framework that unifies low-bit inference and deterministic visual-token pruning.<n> Experiments on standard VLM benchmarks show improved robustness over stage-wise baselines under the same low-bit regime.
  arXiv  Detail & Related papers  (2026-04-19T08:18:29Z)
• KVSculpt: KV Cache Compression as Distillation [7.085426079187912]
  KV cache compression is critical for efficient long-context LLM inference.<n>Existing methods range from pure eviction -- selecting which KV pairs to keep -- to merging, which combines similar pairs into fewer ones.<n>We propose KVSculpt, which moves to the other end of this spectrum.<n>Keys are optimized via L-BFGS and values are solved in closed form via least squares.
  arXiv  Detail & Related papers  (2026-03-29T19:14:25Z)
• BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models [56.504879072674015]
  We propose Bit-Plane Decomposition Quantization (BPDQ), which constructs a variable quantization grid via bit-planes and scalar coefficients.<n>BPDQ enables serving Qwen2.5-72B on a single GTX 3090 with 83.85% GSM8K accuracy (vs. 90.83% at 16-bit)
  arXiv  Detail & Related papers  (2026-02-04T02:54:37Z)
• Dissecting Outlier Dynamics in LLM NVFP4 Pretraining [46.10969678564592]
  This study conducts a longitudinal analysis of outlier dynamics across architecture during NVFP4 pretraining.<n>We find that, compared with Softmax Attention (SA), Linear Attention (LA) reduces per-tensor heavy tails but still exhibits persistent block-level spikes under block quantization.<n>We then develop CHON, an NVFP4 training recipe integrating with post-QK operation protection.
  arXiv  Detail & Related papers  (2026-02-02T12:50:27Z)
• HAS-VQ: Hessian-Adaptive Sparse Vector Quantization for High-Fidelity LLM Compression [0.0]
  We introduce HAS-VQ (Hessian-Adaptive Sparse Vec- tor Quantization), a compression framework that strictly decouples high-sensitivity outliers from the bulk weight distribution.<n>We evaluate HAS-VQ on SmolLM2-1.7B, demonstrating two distinct regimes of superiority.
  arXiv  Detail & Related papers  (2026-01-11T15:35:10Z)
• CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training [73.46600457802693]
  We introduce a new method that counteracts the loss induced by quantization.<n>CAGE significantly improves upon the state-of-theart methods in terms of accuracy, for similar computational cost.<n>For QAT pre-training of Llama models, CAGE matches the accuracy achieved at 4-bits (W4A4) with the prior best method.
  arXiv  Detail & Related papers  (2025-10-21T16:33:57Z)
• Quantile Advantage Estimation for Entropy-Safe Reasoning [44.192277495613695]
  Reinforcement Learning with Verifiable Rewards (RLVR) strengthens LLM reasoning, but training often oscillates between entropy collapse and entropy explosion<n>We trace both hazards to the mean baseline used in value-free RL, which improperly penalizes negative-advantage samples under reward outliers.<n>We propose Quantile Advantage Estimation (QAE), replacing the mean with a group-wise K-quantile baseline.
  arXiv  Detail & Related papers  (2025-09-26T17:37:52Z)
• A Case for Library-Level k-Means Binning in Histogram Gradient-Boosted Trees [0.0]
  We consider a novel approach that replaces quantile binning with a $k$-means discretizer with quantile bins.<n>We test this swap against quantile and uniform binning on 33 OpenML datasets.
  arXiv  Detail & Related papers  (2025-05-18T15:28:06Z)
• KurTail : Kurtosis-based LLM Quantization [51.24081396305435]
  KurTail is a new post-training quantization scheme that mitigates outliers in the activations of large language models.<n>It offers a 13.3% boost in MMLU accuracy and a 15.5% drop in Wiki perplexity compared to QuaRot.<n>It also outperforms SpinQuant with a 2.6% MMLU gain and reduces perplexity by 2.9%, all while reducing the training cost.
  arXiv  Detail & Related papers  (2025-03-03T12:43:06Z)
• Quantize What Counts: More for Keys, Less for Values [63.51476878610841]
  Large Language Models (LLMs) suffer inference-time memory bottlenecks dominated by the attention Key-Value ( KV) cache.<n>This paper proposes two theorems that anchor mixed-precision KV quantization in the intrinsic geometry of Transformer models.
  arXiv  Detail & Related papers  (2025-02-20T22:24:27Z)
• ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals [10.860081994662645]
  Post-training quantization of large language models (LLMs) holds the promise in reducing the prohibitive computational cost at inference time.<n>We propose ResQ, a PTQ method that pushes further the state-of-the-art.<n>We demonstrate that ResQ outperforms recent uniform and mixed precision PTQ methods on a variety of benchmarks.
  arXiv  Detail & Related papers  (2024-12-18T22:01:55Z)
• SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models [61.474101404805545]
  Diffusion models can generate high-quality images, but as they scale, rising memory demands and higher latency pose deployment challenges.<n>We propose SVDQuant, a new 4-bit quantization paradigm to overcome this limitation.<n>We reduce the memory usage for the 12B FLUX.1 models by 3.5$times$, achieving 3.0$times$ speedup over the 4-bit weight-only quantization (W4A16) baseline.
  arXiv  Detail & Related papers  (2024-11-07T18:59:58Z)

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.