KV-Cache Quantization

Orthogonal feature decorrelation is effective for low-bit online vector quantization, but dense random orthogonal transforms incur prohibitive $O(d^2)$ storage and compute. RotorQuant reduces this cost with blockwise $3$D Clifford rotors, yet the resulting $3$D partition is poorly aligned with modern hardware and offers limited local mixing. We propose IsoQuant, a blockwise rotation framework based on quaternion algebra and the isoclinic decomposition of $SO(4)$. It represents each $4$D block as a quaternion and applies a closed-form transform $T(v)=q_L v \overline{q_R}$. This yields two main variants: IsoQuant-Full, which realizes the full $SO(4)$ rotation, and IsoQuant-Fast, which keeps only one isoclinic factor for lower cost; the framework also admits a lightweight $2$D special case. At $d=128$, IsoQuant-Full reduces forward rotation cost from about $2{,}408$ FMAs in RotorQuant to $1{,}024$, while IsoQuant-Fast further reduces it to $512$. Across $18$ fused CUDA settings with $d \in {128,256,512}$, bit widths ${2,3,4}$, and FP16/FP32 execution, IsoQuant achieves mean kernel-level speedups of about $4.5\times$--$4.7\times$ over RotorQuant while maintaining comparable reconstruction MSE, with peak speedups above $6\times$. Current validation is limited to the stage-1 quantize--dequantize path on synthetic normalized vectors; end-to-end KV-cache evaluation remains future work.

Self-forcing video generation extends a short-horizon video model to longer rollouts by repeatedly feeding generated content back in as context. This scaling path immediately exposes a systems bottleneck: the key-value (KV) cache grows with rollout length, so longer videos require not only better generation quality but also substantially better memory behavior. We present a comprehensive empirical study of KV-cache compression for self-forcing video generation on a Wan2.1-based Self-Forcing stack. Our study covers 33 quantization and cache-policy variants, 610 prompt-level observations, and 63 benchmark-level summaries across two evaluation settings: MovieGen for single-shot 10-second generation and StoryEval for longer narrative-style stability. We jointly evaluate peak VRAM, runtime, realized compression ratio, VBench imaging quality, BF16-referenced fidelity (SSIM, LPIPS, PSNR), and terminal drift. Three findings are robust. First, the strongest practical operating region is a FlowCache-inspired soft-prune INT4 adaptation, which reaches 5.42-5.49x compression while reducing peak VRAM from 19.28 GB to about 11.7 GB with only modest runtime overhead. Second, the highest-fidelity compressed methods, especially PRQ_INT4 and QUAROT_KV_INT4, are not the best deployment choices because they preserve quality at severe runtime or memory cost. Third, nominal compression alone is not sufficient: several methods shrink KV storage but still exceed BF16 peak VRAM because the current integration reconstructs or retains large BF16 buffers during attention and refresh stages. The result is a benchmark harness, analysis workflow, and empirical map of which KV-cache ideas are practical today and which are promising research directions for better memory integration. Code, data products, and the presentation dashboard are available at https://github.com/suraj-ranganath/kv-quant-longhorizon/.

We compress KV cache entries by quantizing angles in the Fast Walsh-Hadamard domain, where a random diagonal rotation makes consecutive element pairs approximately uniformly distributed on the unit circle. We extend this angular quantizer with per-layer early-boost, which independently configures K and V codebook sizes at each layer, allocating higher precision to a model-specific subset of critical layers. Across seven models (1B to 7B parameters), per-layer early-boost achieves lossless compression on four models and near-lossless quality on six of seven, at 3.28 to 3.67 angle bits per element. Asymmetric norm quantization (8-bit for keys, 4-bit log-space for values) yields 6.56 total bits per element on Mistral-7B with perplexity degradation of +0.0014 and no calibration data. A layer-group sensitivity analysis reveals model-specific bottleneck patterns, including K-dominated versus V-dominated layers and negative-transfer layers where increased precision degrades quality.

The growing context length of Large Language Models (LLMs) enlarges the Key-Value (KV) cache, limiting deployment in resource-limited environments. Prior training-free approaches for KV cache compression typically rely on low-rank approximation or scalar quantization, which fail to simultaneously achieve high compression ratios and high reconstruction fidelity. We propose VQKV, a novel, training-free method introducing vector quantization (VQ) to obtain highly compressed KV representations while preserving high model fidelity, allowing for the representation of thousands of floating-point values with just a few integer indices. As a result, VQKV achieves an 82.8% compression ratio on LLaMA3.1-8B while retaining 98.6% of the baseline performance on LongBench and enabling 4.3x longer generation length on the same memory footprint.

The KV cache in self-attention has emerged as a major bottleneck in long-context and large-batch inference for LLMs. Existing approaches often treat sparsity prediction and compression as separate modules, relying on auxiliary index structures to select relevant tokens, and on complex quantization schemes to reduce memory usage. This fragmented design introduces redundant overhead and limits scalability. In this paper, we propose a novel paradigm: treating the compressed key representation not merely as storage, but as a self-indexing structure that directly enables efficient sparse attention. By designing a sign-based 1-bit vector quantization (VQ) scheme, our method unifies compression and retrieval in a single, hardware-friendly format. This approach eliminates the need for external indices or learning-based predictors, offering a lightweight yet robust solution for memory-constrained inference. All components are designed to be hardware-efficient and easy to implement. By implementing custom CUDA kernels, our method integrates seamlessly with FlashAttention, minimizing additional runtime and memory overhead. Experimental results demonstrate that our approach delivers both effectiveness and efficiency.

When transformer-based language models are deployed for text generation, most of the inference time is spent in the decoding stage, where output tokens are generated sequentially. Reducing the hardware cost of each decoding step is therefore critical for efficient long-context generation. A major bottleneck is the key-value (KV) cache, whose size grows with sequence length and often dominates the model's memory footprint. Prior work has proposed quantization methods to compress the KV cache while minimizing its loss of precision. We present InnerQ, a hardware-aware KV cache quantization scheme that reduces decode latency without compromising evaluation performance. InnerQ performs group-wise quantization by grouping cache matrices along their inner dimension. This grouping strategy aligns dequantization with vector-matrix multiplication and increases data reuse across GPU compute units. As a result, InnerQ reduces memory access and accelerates dequantization, achieving an average $1.3\times$ speedup over prior KV cache quantization methods and $2.7\times$ over the non-quantized baseline. To maintain fidelity under aggressive compression, InnerQ incorporates three techniques: (i) hybrid quantization, which chooses symmetric or asymmetric quantization for each group based on local statistics; (ii) high-precision windows for both recent tokens and attention sink tokens to mitigate outlier leakage; and (iii) per-channel normalization of the key cache, computed once during prefill and folded into the model parameters to eliminate runtime overhead. Beyond reducing latency, experiments on Llama and Mistral models show that InnerQ also improves few-shot evaluation scores relative to prior KV cache quantization methods.

Learning-based 3D visual geometry models have significantly advanced with the advent of large-scale transformers. Among these, StreamVGGT leverages frame-wise causal attention to deliver robust and efficient streaming 3D reconstruction. However, it suffers from unbounded growth in the Key-Value (KV) cache due to the massive influx of vision tokens from multi-image and long-video inputs, leading to increased memory consumption and inference latency as input frames accumulate. This ultimately limits its scalability for long-horizon applications. To address this gap, we propose XStreamVGGT, a tuning-free approach that seamlessly integrates pruning and quantization to systematically compress the KV cache, enabling extremely memory-efficient streaming inference. Specifically, redundant KVs generated from multi-frame inputs are initially pruned to conform to a fixed KV memory budget using an efficient token-importance identification mechanism that maintains full compatibility with high-performance attention kernels (e.g., FlashAttention). Additionally, leveraging the inherent distribution patterns of KV tensors, we apply dimension-adaptive KV quantization within the pruning pipeline to further minimize memory overhead while preserving numerical accuracy. Extensive evaluations show that XStreamVGGT achieves mostly negligible performance degradation while substantially reducing memory usage by 4.42$\times$ and accelerating inference by 5.48$\times$, enabling practical and scalable streaming 3D applications. The code is available at https://github.com/ywh187/XStreamVGGT/.

Large Language Models (LLMs) are increasingly deployed in scenarios demanding ultra-long context reasoning, such as agentic workflows and deep research understanding. However, long-context inference is constrained by the KV cache, a transient memory structure that grows linearly with sequence length and batch size, quickly dominating GPU memory usage. Existing memory reduction techniques, including eviction and quantization, often rely on static heuristics and suffer from degraded quality under tight budgets. In this paper, we propose ARKV, a lightweight and adaptive framework that dynamically allocates precision levels to cached tokens based on per-layer attention dynamics and token-level importance. During a short prefill phase, ARKV estimates the original quantization (OQ) ratio of each layer by computing statistical scores such as attention entropy, variance and kurtosis. During decoding, tokens are assigned to one of three states, Original (full precision), Quantization (low precision), or Eviction, according to a fast heavy-hitter scoring strategy. Our experiments on LLaMA3 and Qwen3 models across diverse long- and short-context tasks demonstrate that ARKV preserves ~97% of baseline accuracy on long-context benchmarks while reducing KV memory usage by 4x, with minimal throughput loss. On short-context tasks, ARKV matches full-precision baselines; on GSM8K math reasoning, it significantly outperforms uniform quantization. These results highlight the practical viability of ARKV for scalable LLM deployment, offering fine-grained, data-driven memory control without retraining or architectural modifications. The source code and artifacts can be found in: https://github.com/Large-scale-Sustainable-Computing-LSC/ARKV

Multi-agent LLM systems on edge devices face a memory management problem: device RAM is too small to hold every agent's KV cache simultaneously. On Apple M4 Pro with 10.2 GB of cache budget, only 3 agents fit at 8K context in FP16. A 10-agent workflow must constantly evict and reload caches. Without persistence, every eviction forces a full re-prefill through the model -- 15.7 seconds per agent at 4K context. We address this by persisting each agent's KV cache to disk in 4-bit quantized format and reloading it directly into the attention layer, eliminating redundant O(n) prefill computation via direct cache restoration. The system comprises three components: a block pool providing per-agent isolated Q4 KV caches in safetensors format, a BatchQuantizedKVCache for concurrent inference over multiple agents' quantized caches, and cross-phase context injection that accumulates attention state across conversation phases without re-computation. Evaluated on three architectures (Gemma 3 12B, dense GQA, 48 layers; DeepSeek-Coder-V2-Lite 16B, MoE MLA, 27 layers; Llama 3.1 8B, dense GQA, 32 layers), cache restoration reduces time-to-first-token by up to 136x (Gemma: 22--136x at 4K--32K; DeepSeek: 11--76x at 4K--32K; Llama: 24--111x at 4K--16K; 3--10x at 1K). Q4 quantization fits 4x more agent contexts into fixed device memory than FP16. Perplexity measured with actual Q4 KV caches shows -0.7% for Gemma, +2.8% for Llama, and +3.0% for DeepSeek. Open-source at https://github.com/yshk-mxim/agent-memory

Large Language Model (LLM) inference is typically memory-intensive, especially when processing large batch sizes and long sequences, due to the large size of key-value (KV) cache. Vector Quantization (VQ) is recently adopted to alleviate this issue, but we find that the existing approach is susceptible to distribution shift due to its reliance on calibration datasets. To address this limitation, we introduce NSNQuant, a calibration-free Vector Quantization (VQ) technique designed for low-bit compression of the KV cache. By applying a three-step transformation-1) a token-wise normalization (Normalize), 2) a channel-wise centering (Shift), and 3) a second token-wise normalization (Normalize)-with Hadamard transform, NSNQuant effectively aligns the token distribution with the standard normal distribution. This alignment enables robust, calibration-free vector quantization using a single reusable codebook. Extensive experiments show that NSNQuant consistently outperforms prior methods in both 1-bit and 2-bit settings, offering strong generalization and up to 3$\times$ throughput gain over full-precision baselines. Code is available at https://github.com/DHdroid/NSNQuant.