Looped transformers are a parameter-efficient alternative to standard transformers for language modeling. By reapplying the same layers across multiple loop steps, recent looped language models match the performance of non-looped models several times their size. While this architecture effectively reduces parameter memory, each loop step still stores its own keys and values, so the key-value (KV) cache grows linearly with the number of loop steps and becomes the main memory bottleneck. We observe that the KV cache of looped models is highly redundant along the loop axis and that the loop steps differ substantially in their sensitivity to quantization. Based on these observations, we propose $\textbf{LoopVQ}$, a KV cache vector quantization method for looped transformers that codes channels of multiple loop steps jointly, and fine-tunes the codebooks to match the output of the full-precision model. At 0.5 bits per element, LoopVQ outperforms existing KV cache vector quantization methods for standard LLMs on general, long chain-of-thought reasoning, and long-context retrieval tasks with Ouro and Huginn models. Its design is orthogonal to these methods, and combined with TaSQ, it retains much of the BF16 accuracy even at 0.25 bits per element. We also implement LoopVQ in SGLang, where it nearly halves the decode latency at a 32K-token context and raises the peak serving throughput by up to $4.3\times$ and $6.1\times$ on the 1.4B and 2.6B Ouro models compared to the BF16 baseline.
Philipp Nazari, Neehal Tumma, Daniela Rus, T. Konstantin Rusch
Linear recurrences are becoming an increasingly common building block in large language models, replacing the growing KV cache of softmax attention with a fixed-size recurrent state that enables efficient decoding. However, the quantization stack has largely been developed around softmax Transformers, whose numerical properties and inference state differ from those of recurrent models. Our goal is to understand these differences and study the design space of quantization methods for recurrent models. In our analysis, we differentiate between two targets. First, extra-state quantization concerns weights and activations outside the recurrent state, whose distributions are shaped indirectly by the sequence mixer during training. In controlled 1.3B parameter models, we find that decayed recurrences develop weaker residual outlier channels than softmax attention and are therefore easier to quantize without incoherence processing. Second, intra-state quantization concerns the recurrent state itself during decode, where repeated updates create a different numerical problem from KV cache quantization. We instantiate our findings as LoReS, a state quantization pipeline combining value-axis scale grouping to match output channel magnitude, decay-based mixed-precision to protect slowly decaying heads or channels, and stochastic rounding to limit error accumulation under repeated requantization. Across Qwen-3.5 9B, Nemotron-H 8B, and Kimi-Linear 48B-A3B, LoReS supports robust 8-bit state quantization and lower effective precision on shorter decode horizons. We implement LoReS in vLLM and demonstrate end-to-end decode speedups.
Yan Tai, Yunan Ding, Guangzhao Li, Siqi Luo, Chaoyang Zhang, Guangtao Zhai, Guodong Guo, Xiaohong Liu
KV cache quantization is well studied for autoregressive language models, where cached prefix states are exact under causal attention and quantization is mainly a cache reconstruction problem. Diffusion language models (dLLMs) break this assumption. Fast dLLM inference reuses KV states across denoising steps, but bidirectional token representations can change as masked tokens are revealed, so the reused cache may already differ from full recomputation before quantization is applied. We study KV cache quantization under this cache-reuse error. We adapt KIVI and KVQuant to Fast-dLLM-style prefix and dual cache reuse, and introduce TRACE and dLLM-KVQ. TRACE reconstructs feasible dLLM reveal trajectories from prompt-answer pairs, providing calibration states that match iterative masked decoding. dLLM-KVQ uses these trajectories to choose per-layer K-cache entries that remain in high precision according to output- and attention-level behavior metrics, while applying standard low-bit value quantization. Across LLaDA and Dream evaluations on GSM8K, HumanEval, MATH, and MBPP, dLLM-KVQ achieves the highest average score among quantized methods across the reported 4-bit and 2-bit prefix/dual cache settings.
Larger models and longer contexts make the KV cache a memory and bandwidth bottleneck. We introduce Block-GTQ, a framework that uses the two-dimensional frequency blocks of rotary position embeddings (RoPE) to allocate cached-key precision. A blockwise logit-error bound motivates a label-free query-key energy score, which we combine with codec-dependent rate penalties. Under equal-cost budgets and diminishing marginal gains, largest-marginal-gain allocation exactly minimizes the separable integer proxy. We instantiate Block-GTQ with TurboQuant-MSE (TQ-MSE), grouping equal-rate blocks to support attention over packed caches without materializing a decoded fp16 KV cache. Across ten model configurations, K-only diagnostics reduce layer-averaged logit mean absolute error by about 32-80% relative to uniform TQ-MSE, improving all 367 layers at both 2- and 3-bit average logical key rates. At K2V2 (2 average logical bits per K/V coordinate) on Llama-3.1-8B-Instruct, Block-GTQ raises the six-task needle-in-a-haystack (NIAH) average from 70.6 to 97.4 and LongBench-EN from 33.7 to 44.9; K2V2 gains also hold on the tested 32B and 70B models. On DeepSeek-R1-Distill-Qwen-7B at K3V2, without fp16 sink or recent-token buffers, it achieves 49.6/38.8% avg@8 on AIME 2024/2025 versus fp16's 54.2/37.9%, where uniform TQ-MSE scores zero on both. On Qwen2.5-3B-Instruct, packed K3V3 serving on one H800 reduces resident KV footprint by a factor of 3.24 and retains perplexity close to fp16 at 128K, while uniform TQ-MSE degrades severely.
The linear growth of KV cache bottlenecks long-context LLMs, yet RoPE-induced oscillations complicate Key cache quantization. To address this issue, we propose SpectrumQuant, a frequency-domain framework that utilizes the Discrete Cosine Transform (DCT) to convert these oscillations into sparse spectral representations. Specifically, our pipeline integrates dominant frequency extraction, hybrid bit-width allocation, and high-frequency pre-emphasis to maximize fidelity while minimizing memory footprint. To eliminate computational overhead, we develop fused Triton kernels featuring deferred inverse transformation and on-chip sparse accumulation. Extensive experiments on several benchmarks confirm SpectrumQuant achieves efficient compression with performance and latency comparable to FP16 baselines.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Tao Zhang, Ziqian Zeng South China University of Technology, Hao Peng, Huiping Zhuang, Cen Chen South China University of Technology
Long Chain-of-Thought (CoT) reasoning has significantly advanced the capabilities of Large Language Models (LLMs), but this progress is accompanied by substantial memory and latency overhead from the extensive Key-Value (KV) cache. Although KV cache quantization is a promising compression technique, existing low-bit quantization methods often exhibit severe performance degradation on complex reasoning tasks. Fixed-precision quantization struggles to handle outlier channels in the key cache, while current mixed-precision strategies fail to accurately identify components requiring high-precision representation. We find that an effective low-bit KV cache quantization strategy must consider two factors: a key channel’s intrinsic quantization difficulty and its relevance to the query. Based on this insight, we propose MixKVQ, a novel plug-and-play method that introduces a lightweight, query-aware algorithm to identify and preserve critical key channels that need higher precision, while applying per-token quantization for value cache. Experiments on complex reasoning datasets demonstrate that our approach significantly outperforms existing low-bit methods, achieving performance comparable to a full-precision baseline at a substantially reduced memory footprint.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Serving LLMs requires substantial memory due to the storage requirements of Key-Value (KV) embeddings in the KV cache, which grows with sequence length. An effective approach to compress KV cache is quantization. However, traditional quantization methods face significant memory overhead due to the need to store quantization constants (at least a zero point and a scale) in full precision per data block. Depending on the block size, this overhead can add 1 or 2 bits per quantized number. We introduce QJL, a new quantization approach that consists of a Johnson-Lindenstrauss (JL) transform followed by sign-bit quantization. In contrast to existing methods, QJL eliminates memory overheads by removing the need for storing quantization constants. We propose an asymmetric estimator for the inner product of two vectors and demonstrate that applying QJL to one vector and a standard JL transform without quantization to the other provides an unbiased estimator with minimal distortion. We have developed an efficient implementation of the QJL sketch and its corresponding inner product estimator, incorporating a lightweight CUDA kernel for optimized computation. When applied across various LLMs and NLP tasks to quantize the KV cache to only 3 bits, QJL demonstrates a more than fivefold reduction in KV cache memory usage without compromising accuracy, all while achieving faster runtime. Codes are available at \url{https://github.com/amirzandieh/QJL}.