Quantization
-
Few Bits, One Law: Toward W2A4KV2
2026-10-06 22:55:36Kai Yi, Tarek Elgamal, Sruthikesh Surineni, Vignesh Vivekraja, Soumyadeep Ghosh, Steven LiAbstract
Extreme low-bit LLM compression is most challenging when weights, activations, and KV caches are quantized together: their distributions differ, and quantization errors interact throughout the network. We introduce CanonQ, a unified quantization-aware training framework that addresses these challenges by separating source canonicalization from task-aware adaptation. Fixed rotations and energy normalization map heterogeneous tensor sources to canonical coordinates, enabling frozen Gaussian-reference codebooks to be reused across layers and models. Joint training then adapts the network to the coupled errors of weight, activation, and cache quantization within a common scalar/vector interface. We bound frozen-codebook transfer error and local task loss, and derive an exact normalization-aware straight-through Jacobian that links quantization distortion to gradient bias. The strongest gains arise under joint W2A4KV2 compression: across LLaMA3-1B/3B/8B, CanonQ-Omni achieves up to 14.28x lower WikiText-2 perplexity and up to 57.9% higher mean zero-shot accuracy than prior state-of-the-art and representative quantization baselines. The benefits extend to Qwen3-1.7B, code generation, and mathematical reasoning: on instruction-tuned MobileLLM-Pro-1B at W2A16KV16, CanonQ achieves relative improvements of 41.7% in HumanEval pass@1 and 39.1% in GSM8K exact match over the strongest evaluated quantization baseline.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09202
PDF
-
A Systematic Study of Semantic ID Spaces for Generative Information Retrieval
2026-10-06 17:33:32Alexia Allal, Hicham Randrianarivo, Sylvain LamprierAbstract
Generative Information Retrieval (GIR) has emerged as a transformative paradigm, shifting document retrieval from a traditional "retrieve-and-rank" workflow to sequence-to-sequence generation, where a model directly predicts document identifiers (DocIDs). While the semantic design of these DocIDs is known to be critical for performance, a fundamental question remains under-explored: what makes a good DocID? Current approaches rely heavily on computationally expensive downstream evaluations, hindering systematic analysis and rapid iteration. In this work, we address this challenge by presenting a comprehensive study on the properties, metrics, and trade-offs that define effective numerical DocIDs. Specifically, our contributions are threefold: First, we propose a unified framework that unifies Product Quantization (PQ) and Residual Quantization (RQ), and their hybrid variants within a single design space. This enables us to systematically study key DocID properties, such as hierarchy versus parallelism, as well as the impact of hyperparameters like DocID length and codebook size. Second, we define a suite of training-free, intrinsic metrics, to quantify DocID quality and evaluate structural fidelity without the overhead of full model training. Through extensive experiments on MS MARCO 300K and NQ320K, we analyze how these structural properties influence retrieval effectiveness.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08732
PDF
-
ActTune: Action-Aware Precision and GPU Operating-Point Adaptation for Energy-Efficient Vision-Language-Action Inference
2026-10-06 14:35:22Zou Qingyun, Bin Gao, Wenju Zhao, Weng-Fai Wong, Bingsheng He, Tulika MitraAbstract
Vision-language-action (VLA) policies repeatedly invoke inference to control robots, making graphics processing unit (GPU) energy a recurring cost of task execution. Reducing energy per inference call, however, may not reduce energy per successful task if numerical errors increase failures or slower inference prolongs execution. We therefore target GPU energy per successful task while preserving task success and keeping the inference-latency increase within 10\%. Our approach builds on two observations: quantization sensitivity varies across action classes, model layers, and weights versus activations; and numerical precision changes the workload, shifting favorable GPU operating points. We introduce ActTune, an action-aware framework that connects layer-wise precision allocation with workload-dependent GPU operating-point selection over requested frequency--power-cap pairs. A lightweight decision tree learns its splits and leaf precision configurations directly from configuration action errors, then selects precision before each policy call. The controller forecasts the next workload and applies the selected GPU operating point asynchronously using a lookup table calibrated under a latency budget. A shared resident quantized weight bank enables configuration switching without weight reconstruction or additional policy evaluations. On LIBERO, a benchmark for lifelong robot learning, ActTune improves mean task success by up to 2.3\% relative to state of the art. Relative to the original BF16 implementations, it delivers up to $2.02\times$ faster inference and, with GPU operating-point adaptation, reduces energy per successful task by up to 76.8\%.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08444
PDF
-
Test-Time Adaptation of Quantized ViTs via Single-Pass Quantizer-Aligned Recalibration
2026-10-06 13:48:33Hyeongheon Cha, Young D. Kwon, Sung-Ju LeeAbstract
Post-training quantization is a standard route to fitting vision transformers (ViTs) into edge compute and memory budgets, yet quantized models become especially brittle under distribution shift. Test-time adaptation (TTA) addresses such shifts without labels, but most existing approaches are poorly aligned with the constraints of quantized inference. Prevailing TTA methods recover accuracy through backpropagation, while backprop-free methods often still incur overhead from extra forward passes or parameter updates, and lightweight feature- or logit-level methods recover only part of the loss. Across these approaches, a quantization-specific failure mode that amplifies the drop is not directly targeted: under shift, activations occupy frozen quantizers' calibrated ranges differently, distorting their code distribution. We propose Quantizer-Aligned Recalibration (QuAR), a single-pass TTA method tailored to quantized ViTs that neither backpropagates nor updates any model parameters. QuAR recalibrates activations at the input to a frozen quantizer, mapping the test stream's running per-channel statistics back toward the source calibration. On ImageNet-C with ViT-B, QuAR achieves the highest mean accuracy among state-of-the-art backprop-free TTA methods at 3-, 4-, 6- and 8-bit weight/activation precision, outperforming the strongest baseline by 2.28 points at 8 bits and 4.00 at 3 bits, with 46% lower latency and a memory overhead of only 0.17 MB (0.01% of peak inference memory). Analysis and diagnostics trace the gain to a reduced per-channel mismatch at these quantizers, which restores the code distribution the baselines leave unchanged or distort further. A single fixed configuration remains ahead across continual streams, non-i.i.d. label shift, seven out-of-distribution suites, and three other backbones.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08358
PDF
-
OSFP4: Joint Optimization of Diagonal Smoothing and Block Scales for NVFP4 Quantization
2026-10-06 12:17:52Neriah Ben David, Ori Meir, Or OrdentlichAbstract
NVFP4 is an attractive datatype for large language model (LLM) inference, offering compact storage and native tensor-core acceleration. However, preserving accuracy using NVFP4 requires careful quantization. In this work we develop a novel quantization scheme called Optimized Smoothing and Scaling for NVFP4 (OSFP4). For each linear projection it uses a diagonal smoothing matrix whose entries are optimized to minimize the squared matrix-product quantization error under NVFP4, taking into account the rounding procedure that is used (either round-to-nearest, or GPTQ-style successive interference cancellation). This requires performing joint optimization on the smoothing entries as well as the block scales, which is facilitated by analyzing a multiplicative-dither FP4 quantizer instead of the fixed deterministic one. Experiments show that OSFP4 achieves the highest average accuracy among the evaluated competitors in the corresponding quantization settings, while retaining approximately 94-97\% of vendor NVFP4 prefill throughput on the measured workloads. Our code is available in this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.08231
PDF
-
Align, Then Correct: Training-Free Two-Stage Low-Rank Compensation for Extremely Quantized Large Language Models
2026-10-06 11:16:37Seobin Song, Geonho Lee, Janghwan Lee, Jungwook ChoiAbstract
Low-rank quantization error compensation (LQEC) recovers the accuracy lost under aggressive weight quantization by attaching a closed-form rank-$r$ adapter beside each frozen quantized weight, without any training. We show that existing compensators are limited by two shared simplifications. They calibrate symmetrically, evaluating the full-precision and compensated weights on the same activation, which yields a compensation target that is inherently high-rank -- so a fixed rank budget captures only a small fraction of it. And they minimize only the second-order term of the loss, although the compensated model is not stationary: a first-order descent direction larger than the applied compensation itself remains in every layer, and no reconstruction objective can absorb it. We propose a two-stage closed-form framework that removes both simplifications. Stage 1 aligns each layer's output with the full-precision model under a Fisher-weighted asymmetric objective, concentrating the rank budget on a rank-compressible target. Stage 2 re-measures statistics on the compensated model and applies a rank-constrained natural-gradient step that absorbs the remaining first-order signal. Every adapter is the result of a single truncated SVD; backward passes serve only to collect statistics. At 2 bits under QuIP#, our method reduces WikiText-2 perplexity from 12.43 to 10.26 on Qwen3-8B and from 21.11 to 13.22 on Qwen3-4B. On the held-out C4 corpus, it recovers 51% and 84% of the gap to FP16, versus 31% and 63% for the strongest baseline, with consistent gains in the seven-task zero-shot average, at higher bit-widths, and under a distinct quantizer.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08164
PDF
-
Lost in the bf16 Cast: Exporting Ternary Language Models Can Revert Most Low-Learning-Rate Code Changes
2026-10-06 06:58:35Avichal Sahai (Ofbusiness), Nishant Raj (Ofbusiness), Animesh Srivastava (Ofbusiness)Abstract
Ternary language models such as BitNet b1.58, Falcon-E and BitCPM are fine-tuned with higher-precision latent weights and deployed as ternary codes produced by an export step that, in the labs' documented pipelines, first casts the latents to bf16. We audit those pipelines across three labs. In released checkpoints, fp32 quantization of the shipped latents disagrees with the deployed codes on 0.83-1.77% of codes in Falcon-E and BitCPM and on 1.530% in BitNet 2B-4T; for Falcon-E and BitCPM most disagreements are products that bf16 rounding lands exactly on the threshold, which ties-to-even maps to zero, and the unmodified onebitllms exporter reproduces all four Falcon-E releases byte for byte. At fine-tuned endpoints, with learning rates selected to match a nominal learning-rate-to-bf16-ULP ratio, the documented export lowers greedy GSM8K strict accuracy from 58.79% to 0.78% for Falcon-E-1B-Base and from 36.13% to 0.39% for BitCPM-CANN-0.5B, and a bf16 save and reload lowers BitNet 2B-4T's strict accuracy by 27.54 points while its last-number accuracy rises. Two compatibility remedies, writing the training quantizer's codes directly or adjusting the bf16 inputs until the unchanged tools emit them, each met a 4-point strict-accuracy non-inferiority criterion against online evaluation in all three models. In two model families, randomized interventions on the initial distance from the threshold support distance-dependent selection of the codes that fine-tuning changes.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07853
PDF
-
Quantization Effects on Tool-Failure Recovery Vary Across Prompts and Evaluation Designs
Abstract
Post-training quantization reduces the cost of deploying language-model agents, but its effect on recovery from temporary tool failures can depend on how recovery is evaluated. We compare 8-bit and 4-bit variants of Llama-3.1-8B-Instruct and Qwen2.5-7B-Instruct on twenty deterministic tool-use tasks and five prompts. The 8-bit-4-bit recovery comparison changes direction across prompts and evaluation targets. On tasks that both variants complete without faults under the same prompt, the difference ranges from 0 to +20.2 percentage points for Llama and from -50.0 to +35.0 points for Qwen. Full-pipeline point estimates favor 8-bit Llama under all five prompts, whereas the Qwen comparison changes direction across prompts. The evaluation target can also reverse the result. For Llama under one prompt, scoring each variant only on its own clean-passing tasks favors 4-bit by 17.5 points; scoring the same tasks for both variants gives no difference, while scoring the full pipeline favors 8-bit by 28.3 points. Executor leniency is a third such choice. Rescoring the same logs with strict output parsing, which 8-bit Llama violates far more often than 4-bit Llama under that prompt, turns that +28.3 into -15.0 while leaving Qwen essentially unchanged. These findings show that one prompt, one screened task set, and one scoring policy do not establish a stable conclusion about quantized-agent robustness. Evaluations should compare variants on matched tasks, report full-pipeline success for deployment decisions, state the scoring policy, and quantify uncertainty across tasks rather than injected fault sites.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07781
PDF
-
TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
2026-10-06 05:03:47Xin Wang, Hao Yu, Zhengyang Zhuge, Bochao Mao, Zheng Li, Junda Feng, Yuyan Luo, Yi Zhang, Yizhong Cao, Mi Zhang, Dayiheng Liu, Jianwei ZhangAbstract
Reinforcement learning (RL) for post-training large language models (LLMs) incurs substantial computation and memory overhead during rollout generation, which motivates low-precision rollout for efficient RL training. However, existing FP4 RL methods suffer from a key limitation: they primarily optimize quantization accuracy on the training and rollout paths independently rather than directly reducing the discrepancy between the two quantized execution paths. In this work, we propose TRACE (Train-Rollout Quantization Alignment via Compact GuidancE), an FP4 quantization framework for RL training of Mixture-of-Experts (MoE) language models that addresses the limitation of existing FP4 RL methods. TRACE incorporates rollout-guided quantization-aware training that uses rollout-side quantization outcomes to guide training-side FP4 rounding decisions, directly reducing train-rollout discrepancy. Moreover, TRACE adopts an efficient quantization-information caching scheme that selectively retains mantissa and scale information from deeper layers to reduce the storage and communication overhead introduced by rollout guidance. We evaluate TRACE on four large-scale MoE language models across reasoning, coding, and long-horizon RL tasks. Our results demonstrate that TRACE enables joint FP4 weight/activation and FP4 KV-cache rollout with RL performance comparable to BF16 rollout, while achieving up to 5.4xrollout speedup and strong final FP4 performance compared with post-hoc FP4 quantization of BF16-trained policies.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07767
PDF
-
AlignQuant: Tile-Aligned Mixed-Precision Quantization for Efficient LLM Generation
2026-10-05 22:06:04Hanzhi Zhang, Qiao Zhang, Qinglei Cao, Heng Fan, Yan Huang, Kewei Sha, Yunhe FengAbstract
Fine-grained mixed-precision quantization promises efficient large language model inference, but local precision choices can conflict with regular GPU storage and computation units. This precision-boundary mismatch limits the translation of compression into practical acceleration. We introduce AlignQuant, a post-training quantization method that uses GPU-compatible two-dimensional weight tiles as the common unit of precision allocation, compact storage, and execution. This shared partition lets precision follow sensitivity within output channels. Joint prefill/decode calibration scores precision reductions using projection-output perturbations weighted by language-model loss gradients under quantized activations. Phase-normalized scores prioritize higher precision for tiles important to either phase under a model-wide weight-storage budget. Each tile stores one selected representation, while phase-specialized kernels reuse the packed model and expand lower-bit weights for INT8 computation with 8-bit activations. Across four LLMs spanning 3B to 14B parameters, AlignQuant achieves up to $2.50\times$ generation speedup over BF16 while preserving model quality. Evaluations further cover three GPUs and contexts up to 64K tokens. These results show that local precision flexibility and regular GPU execution can coexist through a shared tile unit. The implementation is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07457
PDF
-
Cascadia: Resident 975B MoE Inference on Eleven AI PCs
2026-10-05 18:29:24Tate Berenbaum (Not Community Labs Inc.), Matias Parij (Not Community Labs Inc.), Muthaiah Venkatachalam (Intel Corporation)Abstract
Mixture-of-experts models make nearly trillion-parameter capacity accessible with sparse per-token computation, provided that the serving system can distribute the weights and coordinate their execution. We present Cascadia's resident execution of Inkling, a 975B-total/41B-active-parameter model, on eleven Intel Core Ultra X7 358H AI PCs, each with 64 GB of memory, Arc B390 integrated graphics and gigabit Ethernet. We contribute a custom resident MoE engine that preserves Inkling's routing rules, constructs compressed graphs for OpenVINO's fused iGPU primitives, and coordinates FP16 expert computation with FP32 output restoration. The engine fits six consecutive decoder layers per machine and represents dense feed-forward blocks as all-active expert slices, reducing measured dense-layer call time from approximately 8.1 to 4.5 ms. A streaming pipeline coordinates concurrent generation, while captured-state draft evaluation measures agreement with the deployed numerical path. Paired measurements at fifteen concurrency levels from 1 to 176 streams reach 60.29 aggregate decode tokens/s at 88 streams, with 46.87 tokens/s over the complete serving phases. At fifteen streams, median first-token latency is 6.05 s. Raising the context budget from the 1,024-position default, real prompts of 1k to 64k tokens recover the embedded code in all 19 measured answers, with first-token time growing as $aN+bN^2$ and decode latency growing approximately linearly, both bounded by a single-threaded CPU attention loop rather than by memory, which holds 512k positions per stream. Evaluation on captured fleet states separates the effects of vocabulary selection and weight quantization on draft agreement. Together, these contributions establish an execution and evaluation approach for large sparse models on distributed client systems with shared CPU-GPU memory.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07219
PDF
-
CALR: Continuous Anchored Latent Reasoning via Render-of-Thought Compression
2026-10-05 18:00:56Zhaoyang Wei, Bowen Jiang, Yanchao Hao, Wenchao Ding, Zheng Wei, Shaocheng Wu, Zhenjun Han, Jianbin JiaoAbstract
Visual latent reasoning compresses rendered derivations into compact intermediate states, reducing textual reasoning overhead. Existing approaches differ in how they represent these states: continuous methods avoid vocabulary constraints, whereas discrete methods improve accuracy through quantization into a finite codebook. Our analysis of representative continuous and discrete systems identifies two functional requirements: answers must rely on latent states, and those states must carry valid, problem-specific reasoning. Continuous latents influence answers despite collapsed reasoning content, whereas discrete latents retain recoverable intermediate reasoning that answer prediction largely bypasses. To address these challenges, we propose Continuous Anchored Latent Reasoning (CALR), which connects latent formation with answer use through functional anchoring. With reference latents from information-balanced compression, CALR couples latent-mediated answer supervision with derivation-level semantic anchoring: the former routes answer supervision through intermediate states, while the latter grounds their decoded content in problem-specific derivations. A parallel-to-autoregressive curriculum develops sequential reasoning by conditioning subsequent latent blocks on generated prefixes. Evaluations on five mathematical reasoning benchmarks across model families show substantial accuracy gains. Under matched budgets, CALR gains 26.0 percentage points over a comparable continuous latent reasoning method. Further analyses show that its latents support answer prediction and carry problem-specific intermediate reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07175
PDF
-
Investigating Model Compression for Neural Machine Translation in the Biomedical Domain
2026-10-04 19:01:38Maria Zafar, Souhail Bakkali, Rejwanul HaqueAbstract
Large-scale pretrained transformer models have achieved state-of-the-art performance across diverse machine translation tasks, including multilingual settings. Knowledge distillation has emerged as a sustainable approach for model compression, transferring knowledge from large teacher models to smaller, more efficient student models. Similarly, quantization, which reduces the numerical precision of model weights and activations (e.g., from 32-bit to 8-bit representations) is widely used to accelerate inference, enabling models to run several times faster during deployment. However, both techniques face limitations when applied to specialized domain data, particularly under low-resource conditions. In knowledge distillation, the effectiveness of transfer is often constrained by the scarcity of domain-specific parallel data, while quantization can lead to performance degradation as bit precision decreases. In this work, we investigate the combined application of knowledge distillation and quantization for French-to-English biomedical translation, a domain characterized by specialized terminology and limited parallel resources. We develop and compare multiple fine-tuning strategies to adapt compressed student models to this challenging setting. Our experiments demonstrate that a collaboratively distilled and quantized student model achieves a 69% reduction in size, a 98.21% increase in inference speed, and a 98.46% reduction in CO2 emissions compared to the original baseline all without sacrificing translation quality. These results indicate that jointly optimized compression techniques can yield efficient, high-performance models suitable for translation service providers operating under resource constraints.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07032
PDF
-
Offline AI Modules: Voice-First Offline Architecture, Hardware Reference Stack, Quantization and Benchmarking
2026-10-04 17:16:45Sunday Afariogun, Odunolaoluwa Jenrola, Zeinab NezamiAbstract
The Offline AI Modules workstream enables practical, low-power, and community-accessible deployment of voice-first AI systems that operate fully offline. Designed for African language communities where speech is the dominant mode of interaction and internet connectivity is unreliable or absent, the workstream delivers three reinforcing components: a modular voice-first offline architecture, a low-cost hardware reference bill of materials, and a reproducible quantization and a reproducible quantization and benchmarking pipeline for instruction-tuned language models in the 2-5B parameter class. This paper presents the first end-to-end benchmark evaluation of the stack across two hardware tiers: an NVIDIA Jetson Orin NX (TierB) and a Raspberry Pi5 (TierA). Three instruction-tuned models are evaluated across four quantization formats, assessed for deployment metrics (decode throughput, chat latency, memory, power) and multilingual quality (topic classification accuracy on MasakhaNEWS across English, Hausa, Igbo, Nigerian Pidgin, and Yoruba; per-language perplexity drift). Speech recognition is evaluated using Ethio-ASR on Amharic and Oromo across both tiers. The principal finding is that Q4_K_M quantization represents the best size-to-quality trade-off for deployment on both tiers: gemma-4-E2B-it achieves 28.8t/s decode throughput and 89.2% topic classification accuracy at Q4_K_M on TierB, while all three models run within the 16GB memory budget on TierA.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07026
PDF
-
MRVQ: One Resident Index for Dimension- and Rate-Elastic Vector Search
2026-10-02 17:33:13Sean Culatana, Shang-En Huang, Kang LiAbstract
Dense-retrieval services must switch among embedding-prefix dimensions and index bit rates as latency, quality, and memory budgets change. Tuning a quantizer separately for each rate gives the best quality, but the retrieval tier then holds several code streams and quantizer states at once. We introduce Matryoshka Residual Vector Quantization (MRVQ), a post-hoc residual quantizer for frozen embeddings. Its maximum-rate code can be truncated two ways: dropping residual stages lowers the rate, and dropping embedding coordinates lowers the dimension. One resident artifact therefore serves every (dimension, rate) pair we evaluate. Across FiQA and NFCorpus, four embedding families, and {4, 8, 16}-byte codes, MRVQ is the lowest-RAM design we evaluate. It uses 17.8-22.0x less memory than three separately trained QINCo2 indices, and 1.89-2.02x less than a lean shared-model steelman. The saving is not free: per-rate QINCo2 is 0.026-0.107 nDCG@10 better on FiQA. But MRVQ beats PQ, OPQ, and AdANNS-OPQ at matched code size. We also evaluate a low-build-cost PCA-scalar design that attains quality comparable to RaBitQ and its extension while fitting 420x faster at the median. Finally, we report two negative results: QINCo2 collapses when trained at high rates, and a ranking-bound hypothesis misses its pre-specified acceptance criteria. MRVQ is therefore a low-memory operating point for elastic retrieval, not a universal quality winner.
Abstract (translated)
URL
https://arxiv.org/abs/2610.03651
PDF
-
Transform-Aligned Learned Features for Lossy Point Cloud Attribute Compression
2026-10-02 13:40:13Yueru Chen, Pengpeng Yu, Dingquan Li, Wei Gao, Wei Zhang, Fei SongAbstract
Transform-based methods provide an effective framework for point cloud attribute compression by representing attributes as transform coefficients. Introducing learned spatial context into this framework requires mapping spatial representations to the transform domain, but this known basis change is often left for the network to learn implicitly. We propose Transform-Aligned Learned Features (TALF) by applying the attribute transform to learned spatial representations, explicitly aligning them with the coding targets. Our analysis shows that the resulting features exactly represent the first-order prediction term of a smooth nonlinear model, with a bounded Taylor remainder. We integrate TALF into a transform-based attribute codec with explicit coefficient prediction and conditional residual entropy modeling under a unified coefficient-domain rate--distortion objective, while retaining explicit quantization-step control. Extensive experiments across three benchmark datasets and multiple transform bases demonstrate that TALF improves rate--distortion performance over conventional and learned baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2609.34834
PDF
-
VisionMX: Unlocking Microscaling Post-Training Quantization for Vision Models
2026-10-02 12:32:36Elad Dror Cohen, Ofir Gordon, Lior Dikstein, Idan Achituve, Hai Victor HabiAbstract
Microscaling (MX) formats are emerging as a hardware-supported approach to efficient training and inference. They combine low-precision elements with shared block scales, but their impact on vision models remains underexplored. We systematically investigate post-training MX quantization across vision models and tasks. An analysis of direct conversion identifies three sources of error: block-scale representation, the poor alignment of some small convolutional weight tensors with nonuniform element grids, and the underuse of signed codes by nonnegative activations. These findings motivate VisionMX, a post-training MX quantization method that optimizes bounded weight rounding and applies a foldable affine correction to activations. We evaluate VisionMX across image classification, object detection, semantic segmentation, and low-light image enhancement using several MX-style formats. It improves on direct conversion and the evaluated post-training quantization baselines, with the largest performance recoveries in architectures most sensitive to MX conversion
Abstract (translated)
URL
https://arxiv.org/abs/2610.03218
PDF
-
Tailoring the Quantization Space for 1-Bit KV Cache Compression
2026-10-02 09:04:25Minsoo Cheong, Donghyun Son, Sungjoo YooAbstract
The key-value (KV) cache becomes a major memory bottleneck in long-context LLM inference, placing substantial pressure on memory capacity and bandwidth. To mitigate this bottleneck, vector quantization (VQ) has emerged as a promising approach for aggressive KV cache compression. However, existing VQ methods degrade substantially in the 1-bit regime. At such extreme compression, each codebook must represent a larger group of channels with a limited set of centroids, making effective use of its capacity increasingly challenging. To address this, we introduce $\textbf{TaSQ}$, which tailors the VQ target space by combining query-guided channel weighting, cross-head normalization, and covariance-aware channel grouping to better reflect the error sensitivity and statistical structure of cached activations. Since these transforms are RoPE-compatible and can be easily merged into projection weights and codebooks, TaSQ preserves the conventional VQ lookup structure and adds negligible serving overhead. Across general, long-chain-of-thought reasoning, and long-context retrieval benchmarks, TaSQ consistently outperforms existing low-bit KV cache VQ baselines while preserving reasoning stability. On a single RTX 6000 Ada GPU, its SGLang implementation supports up to $14\times$ larger batch sizes and achieves $1.87\times$ higher peak throughput compared to the BF16 baseline.
Abstract (translated)
URL
https://arxiv.org/abs/2610.03027
PDF
-
Rethinking Fixed Temporal Grids: Frequency-Disentangled Motion Generation
2026-10-02 08:44:25Yunjiao Zhou, Junlang Qian, Gen Li, Xinying Guo, Lihua Xie, Jianfei YangAbstract
Most human motion generation methods encode motion as tokens on a uniform temporal grid, where every token spans the same fixed time window. Human motion, however, is temporally heterogeneous: slowly evolving global trajectories coexist with rapid transient events such as foot contacts and joint impulses. Forcing such multi-scale dynamics onto tokens of identical temporal resolution entangles motion frequencies, leaving slow regions redundant while smoothing out the rapid details that distinguish realistic motion. We propose \textbf{FreqMo}, a scale-adaptive motion representation that decomposes motion into wavelet frequency bands, separating dynamics across temporal scales while preserving temporal localization and exact reconstruction. Unified Frequency Residual Quantization (UFRQ) then encodes all bands within a single shared codebook, compressing the token sequence threefold and enabling stable single-stage generation. Experiments show FreqMo attains SOTA fidelity with substantially improved high-frequency preservation, and the same decomposition transfers to continuous diffusion backbones.
Abstract (translated)
URL
https://arxiv.org/abs/2610.03012
PDF
-
CHASE-VLA: Post-Training Quantization Framework for Vision-Language-Action Models with Chunk-Aware Scale Estimation
2026-10-02 01:34:55Jin Hyun, Jung Gyu Min, Gyuhyun Jung, Youngjoo LeeAbstract
Vision-Language-Action (VLA) models map visual observations and language instructions to continuous robot actions, but a diffusion-based action expert (AE) poses a key challenge for low-bit post-training quantization (PTQ). The AE is repeatedly invoked across denoising steps and policy queries, where fixed calibration scales can be mismatched with activation ranges that vary with denoising progress and intended motion. We propose CHASE-VLA, a chunk-aware PTQ method that exploits a VLA-specific signal readily available from the policy: the generated action chunk, including its unexecuted future suffix. Rather than relying only on static scale matching for AE layers, CHASE-VLA combines the previously generated chunk as causal action context with denoising step group information to adapt AE activation scales. This enables W4A4 quantization of both MLP and attention projections in the repeated AE without modifying the pretrained policy. On LIBERO, CHASE-VLA achieves 97.3% average success rate on $\pi_{0.5}$ when both MLP and attention projections in the AE are quantized to W4A4, restoring FP16-level performance. CHASE-VLA also reduces the weight storage of the quantized AE linear layers by 73.4% and their single-chunk memory traffic by 70.9% and 71.2% on $\pi_{0.5}$ and GR00T N1.6, respectively, with a predictor overhead of at most 1.26% of the saved storage.
Abstract (translated)
URL
https://arxiv.org/abs/2610.02666
PDF
