Quantization
-
SCULPT: Training Edge Vision Models for Post-Training Quantization Readiness
2026-09-01 18:10:19Bharadwaj Kavuri, Sourav Babu-PK, Varadhraj Ellapan, Pullarao Maddu, Prasad DeshpandeAbstract
Edge vision models are difficult to deploy on resource-constrained hardware, making low-bit post-training quantization (PTQ) attractive. In practice, standard FP32 training often produces heavy-tailed activation distributions whose outliers destabilize activation quantization: preserving the full range wastes quantization bins on rare extremes, while aggressive clipping causes information loss. Existing solutions typically rely on quantization-aware training (QAT), which adds training complexity and bit-width coupling, or advanced PTQ procedures that repair the model after training. We present SCULPT (Statistical Clipping and Uniform Loss for Post-Training), a training-time method that improves PTQ readiness during ordinary FP32 fine-tuning. SCULPT combines a topology-aware activation regularizer that suppresses quantization-hostile skewness and kurtosis with a stable percentile-based clipping mechanism that learns deployment-ready activation bounds. Unlike QAT, SCULPT does not simulate quantization during optimization; unlike post hoc outlier-repair PTQ methods, it does not require runtime activation transformations. The learned clipping bounds can be exported directly into a standard PTQ workflow for low-bit deployment, including INT8 and lower-bit settings such as W4A8.
Abstract (translated)
URL
https://arxiv.org/abs/2609.01743
PDF
-
The Structure of Quantization Damage in LLMs: Why the Next Bit Should Be Spent Globally
2026-09-01 17:53:41Jundong Hu, Shekar RamachandranAbstract
Post-training quantization (PTQ) is widely used to reduce the cost of serving large language models (LLMs), but its accuracy cost is uneven and is often tuned per model. We study where quantization damage occurs and how to allocate a small additional precision budget. Using causal mixed-precision intervention as ground truth (raise each layer to 8-bit in turn and measure the accuracy it recovers) across 9 open-weight models in 4 architecture families, we test 3 intuitive hypotheses: that quantization damage lives in task circuits, where the model computes, or in weight statistics. None of them predicts which layers benefit from restored precision. Recovery is instead diffuse: for 8 of 9 models, recovering 75% of the gap takes roughly half the layers; the lone exception, Qwen3-8B, is sharply concentrated. At a matched precision budget, spending it globally on finer quantization granularity beats locally repairing the most recoverable layers for all 8 group-128-compatible models (all but OpenLLaMA, whose width rules out group-128), by 21-52 points, including the concentrated Qwen3-8B. We report 2 secondary findings: the residual is budget-limited (8-bit is near-lossless in our evaluation across RTN, GPTQ, and AWQ), and the location of peak recovery correlates with architecture within a family, though not across families. Within this budget setting, global granularity is a better default than selectively protecting critical layers. More broadly, cheap signals that correlate with quantization damage do not necessarily identify where restoring precision improves accuracy; this must be tested with causal intervention.
Abstract (translated)
URL
https://arxiv.org/abs/2609.01587
PDF
-
Compressing AI Traffic: Standardized Neural Network Coding of Visual-Token Representations in Split Vision-Language Inference
2026-09-01 13:07:32Reza Heidari, Hamed R. Tavakoli, Juho KannalaAbstract
When the visual encoder and the language decoder of a vision-language model (VLM) run on different compute nodes, the intermediate visual-token embeddings become a communicated payload rather than an internal activation. We call such machine-consumed intermediate tensors AI traffic and ask how far they can be compressed with a standardized, training-free codec. We insert ISO/IEC 15938-17 Neural Network Coding (NNC) round trips on the complete visual interface of a Qwen3-VL-8B-Instruct video question answering pipeline, comprising the main visual-token representation and the DeepStack feature streams, while leaving weights, prompts, and generation untouched, and sweep the quantization parameter (QP) over a wide rate range. Closed-ended Video-MME accuracy remains close to the uncompressed reference up to a 98% reduction of the transmitted BF16 tensor and only then collapses; open-ended MLVU generation shows the same plateau-and-collapse profile under an LLM judge. This robustness is not due to near-lossless reconstruction: the decoded tensor is heavily discretized, carries substantial row-wise relative L2 error, and has a visibly steeper singular-value decay than its source. Downstream reasoning therefore depends on coarse structure and relative geometry rather than exact floating-point values, which argues for rate-task rather than rate-distortion optimization of AI traffic codecs.
Abstract (translated)
URL
https://arxiv.org/abs/2609.01200
PDF
-
Artificial Rosetta Stone: Constrained Maximum A Posteriori Reconstruction of Symbolic Raga Sequences via Order-k Markov Models
2026-09-01 10:59:12Saanvi Raghavendran (Abstract Math Institute), Abhishek Bhattacharjee (Abstract Math Institute)Abstract
Reconstructing a damaged musical fragment is an inverse problem: the observed sequence contains partial information, while a raga encodes constraints limiting allowable completions. This paper formalizes a mathematical framework for this, proposing the Artificial Rosetta Stone (ARS). We separate three claims often conflated: a symbolic sequence can be reconstructed probabilistically; a sequence can be consistent with an explicit grammar; and a historical performance can be authenticated. We only support the first two. We model a raga via a finite alphabet and constraint system, using an order-k Markov model for melodic probabilities. A symmetric Dirichlet prior yields a tractable posterior. We pose missing-note reconstruction as a constrained MAP problem. For fixed-length sequences and finite-order constraints, optimization admits an exact dynamic-programming solution with worst-case time complexity $O(TN^{k+1})$. We derive the parameter count $N^k(N - 1)$, prove a concentration bound under explicit mixing assumptions, and analyze estimation error propagation. A reproducible synthetic experiment uses six raga-inspired alphabets, orders $k \in \{1, 2, 3\}$, and masking rates up to 50%. This is a proof of concept, not historical reconstruction. A real-audio feasibility pilot evaluates 30 usable sequences from 42 Yaman clips via automated pitch extraction, segmentation, and quantization. Lacking documented provenance and relying on automated transcription, this is not expert-validated archival reconstruction. Claims are tied to stated conditions, not universal properties of Hindustani music. Code: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.01064
PDF
-
Channel-Adaptive Edge AI: Maximizing Inference Throughput by Adapting Computational Complexity to Channel States
2026-09-01 09:04:13Jierui Zhang, Jianhao Huang, Kaibin HuangAbstract
\emph{Integrated communication and computation} (IC$^2$) has emerged as a new paradigm for enabling efficient edge inference in sixth-generation (6G) networks. However, the design of IC$^2$ technologies is hindered by the lack of a tractable theoretical framework for characterizing \emph{end-to-end} (E2E) inference performance. The metric is highly complicated as it needs to account for both channel distortion and artificial intelligence (AI) model architecture and computational complexity. In this work, we address this challenge by developing a tractable analytical model for E2E inference accuracy and leveraging it to design a \emph{channel-adaptive AI} algorithm that maximizes inference throughput, referred to as the edge processing rate (EPR), under latency and accuracy constraints. Specifically, we consider an edge inference system in which a server deploys a backbone model with early exit, which enables flexible computational complexity, to perform inference on data features transmitted by a mobile device. The proposed accuracy model characterizes high-dimensional feature distributions in the angular domain using a Mixture of von Mises (MvM) distribution. This leads to a desired closed-form expression for inference accuracy as a function of quantization bit-width and model traversal depth, which represents channel distortion and computational complexity, respectively. Building upon this accuracy model, we formulate and solve the EPR maximization problem under joint latency and accuracy constraints, leading to a channel-adaptive AI algorithm that achieves full IC$^2$ integration. The proposed algorithm jointly adapts transmit-side feature compression and receive-side model complexity according to channel conditions to maximize overall efficiency and inference throughput. Experimental results demonstrate its superior performance as compared with fixed-complexity counterparts.
Abstract (translated)
URL
https://arxiv.org/abs/2603.03146
PDF
-
A Closed-Loop Evaluation of Capability Loss and Recovery in Compressed Driving Policies
2026-09-01 04:50:17Ahmad Alfan Alfian Irfan, Nur Ahmad Khatim, Mansur AriefAbstract
Many automobile and mobility companies deploy learned driving policies on embedded computers with limited memory and power. Pruning, knowledge distillation, and quantization are the standard methods to reduce the size and the inference cost of these policies. However, these methods are commonly assessed by aggregate numerical scores, and such scores may not reflect the ability of the policy to drive safely when interacting with other road users. In this study, we propose a stage-wise closed-loop evaluation approach to follow a driving policy through a compression pipeline. We formulate the driving task as a partially observable Markov decision process (POMDP) and train a belief-state policy with proximal policy optimization (PPO) in Gym-Duckietown. We then extract the actor, compress it one stage at a time, and evaluate it on five driving curricula. We show that structured pruning is the stage at which the driving capability is first lost. Meanwhile, distillation improves the pruned actor, but the improvement is limited by its rehearsal data. Integer quantization of the improved actor loses some of the curricula that require the vehicle to stop and then resume. Interestingly, the same procedure on the unpruned actor preserves all five curricula. Our study thus provides an empirical analysis aiming to answer the currently active discussions on how to accept a compressed driving policy, so as to achieve a safe and statistically reliable deployment of automated driving functions.
Abstract (translated)
URL
https://arxiv.org/abs/2609.00718
PDF
-
Triple-Bottom-Line Sustainability of Language Models for Edge AI: A Comparison Between SLMs and Quantized LLMs
2026-09-01 03:44:18Jainil Dharmil ShahAbstract
Edge-AI model selection is commonly driven by one isolated metric - accuracy, latency, memory, energy, or safety, even though a deployable language model must balance all five. Our work focuses on answering the question whether na- tively trained small language models (SLMs) or large language models (LLMs) compressed through post-training quantization offer the more sustainable edge- deployment trade-off. We introduce a reproducible Holistic Sustainability Score (HSS) organized around the triple bottom line: an economic pillar for capability and systems efficiency, an environmental pillar for operational GPU energy and a social pillar for harmful-prompt robustness. Five BF16 SLMs and five LLMs under different quantization approaches - BF16, INT8, NF4 4-bit, GPTQ 4-bit, and GGUF Q4 produce 30 measured configurations. Capability is assessed on five zero-shot benchmarks; efficiency uses latency, throughput, peak VRAM and energy; and safety is approximated by attack success rate on five harmful prompts. Qwen3-30B-A3B/GGUF Q4 ranks first in the combined pool (93.38), followed by Mistral-Small-24B/GGUF Q4 (92.40), while Phi-4-mini/BF16 is the highest- ranked SLM in that pool (89.49). Thus, the hypothesis that native SLMs must be the most sustainable edge choice is not supported universally; optimized quantized LLMs can win overall, while SLMs remain competitive through lower resource demand. Quantization is a systems-level choice rather than a monotonic precision- efficiency trade-off and HSS remains relative to its comparison pool and proxy definitions.
Abstract (translated)
URL
https://arxiv.org/abs/2609.00665
PDF
-
Drift-Aware LLM Routing with Sparse Contexts and Shared Budgets
2026-09-01 03:39:59Cheung Hao Lee, Patrick WongAbstract
A multi-model language service must route each request while preserving workload-level budgets for compute, latency, memory, or monetary cost. Two features make this problem materially harder than static model selection. Prompt representations are high dimensional, so only a small subset of embedding directions may predict the incremental value of a model, and both the request mix and the model frontier drift after launches, fine-tunes, quantization changes, and system updates. We formulate nonstationary sparse contextual routing with multiple knapsack constraints and an optional shadow-audit stream that evaluates a small fraction of prompts on several models. We propose Drift-Aware Sparse Routing (DRS). The policy estimates reward and resource use from a rolling audit window, routes using pessimistic reward and optimistic cost estimates, updates resource shadow prices online, and applies a hard meter before commitment. The analysis separates control from statistics. On any event with uniform prediction radii $\{\beta_t\}$, regret against a paced dynamic fluid benchmark is bounded by the sum of the radii, a capacity-buffer term, and an $O(\sqrt{T})$ pacing term. Under a sparse linear model and bounded drift $V_T$, rolling estimation gives \[ \widetilde O\left( T\sqrt{\frac{s}{\rho W}}+WV_T+\sqrt{T} \right), \] where $s$ is sparsity, $\rho$ is the audit rate, and $W$ is the window length. Optimizing $W$ yields the usual stationary $O(\sqrt{sT/\rho})$ rate when $V_T=0$ and a $O(T^{2/3}(s/\rho)^{1/3}V_T^{1/3})$ adaptation term under drift.
Abstract (translated)
URL
https://arxiv.org/abs/2609.00662
PDF
-
BiMTokenizer: Preserving Semantic-Acoustic Balance in Low-Bitrate Speech Tokenization via Bidirectional State-Space Modeling
2026-09-01 01:56:37Xin Zhang, Lin Li, Chuanbo Liu, Jianquan Liu, Kong Aik LeeAbstract
Speech codecs serve as bridges between continuous speech signals and large language models, yet face an inherent conflict between acoustic fidelity and semantic preservation. To mitigate this conflict, recent works increasingly adopt dual-tower architectures to decouple semantic and acoustic modeling with separate encoders. However, these dual-tower designs incur substantial architectural overhead. To avoid such complexity, we revisit the single-tower paradigm and propose BiMTokenizer, a low-bitrate speech codec (around 1.1 kbps) combining a bidirectional state-space backbone with Residual Spherical Leech Quantization (RSLQ). The bidirectional backbone strengthens temporal modeling, while RSLQ offers a fixed, well-separated lattice bottleneck for robust semantic and acoustic tokenization without learned-codebook collapse. Experiments show that BiMTokenizer achieves superior acoustic reconstruction and the lowest WER among low-bitrate codec baselines across both clean and noisy environments, while using less than half the parameters of recent dual-tower baselines. Furthermore, its robust semantic representations yield strong performance on downstream speech understanding tasks, confirming that a well-designed single-tower codec can preserve the semantic-acoustic balance at low bitrates. The code and model weights are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.00562
PDF
-
HBQ: Hierarchical Scaling Block Quantization with Hardware-Efficiency-Aware Design for Accurate LLM Inference
2026-08-31 22:39:52Chun-Ting Chen, Dongmin Han, Hangyeol Mun, Jake Hyun, Arnab Raha, Amit Agarwal, Mark Anders, Mohamed Abdelfattah, Jae-sun SeoAbstract
Block Quantization (BQ) is a promising approach for efficient deployment of large language models (LLMs), enabling low-precision computation with controlled accuracy degradation. Compared to scalar weight-only quantization (WoQ), BQ quantizes both weight and activation, offering higher hardware efficiency and end-to-end inference on a unified datapath, but its design space, spanning bit-width, block size, scaling, and numeric formats, remains underexplored. We provide hardware/benchmark results through design space exploration (DSE). We find that increasing block size improves hardware efficiency by amortizing dequantization and accumulation costs, but degrades accuracy. This trade-off limits conventional BQ methods. Motivated by this insight, we propose Hierarchical Block Quantization (HBQ). Unlike prior methods [1], [2], which use small blocks and conventional Power-of-Two (PoT) or integer-based scaling, HBQ uses large blocks to maximize efficiency and introduces low-overhead significand (SIG) scaling for second-level quantization. By allocating quantization levels effectively and accounting for distinct activation and weight distributions, SIG scaling compensates for large-block errors more effectively than prior PoT and INT schemes. HBQ-A (accurate) achieves W4A16-level accuracy using only W4A5 while requiring less silicon area than NVFP4. HBQ-E (efficient) further reduces hardware cost by 17% while maintaining higher accuracy than all existing BQ methods. We implemented a 28nm ASIC accelerator applying HBQ to weights, activations, and KV cache, and integrated a novel partial-sum BQ scheme to further reduce EMA energy. Compared to state-of-the-art WoQ, HBQ delivers $2.3\times$/$4.6\times$ higher area/energy efficiency at the same accuracy level; $1.6$--$3.3\times$ system energy reduction and $1.5$--$3.0\times$ speedup over prior BQ methods while providing best accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2609.00450
PDF
-
QTEA: Ternary LLMs with Sparse Residual Salient Weight and By-Column Optimization
2026-08-31 18:33:36Yipin Guo, Arun M George, Jie Fu, Tareq Mahmoud, Sixue Xing, Siddharth JoshiAbstract
Weight-only post-training quantization (PTQ) can alleviate the computational burden of serving large language models (LLMs) at scale. However, existing PTQ methods often fail to generalize across models and suffer severe accuracy loss below 2 bits. Many leverage unstructured sparsity to mitigate this loss, but at the cost of regularity and GPU-friendly execution. We present QTEA, a sub-2-bit PTQ framework that quantizes weights into ternary values and uses salient weights as residual error compensators. To maintain hardware efficiency, residuals are assigned to selected columns with semi-structured \(1{:}4\) sparsity within the salient columns. We further add column-wise rescale refinement to GPTQ-style column-by-column quantization, alternately updating per-column scales and ternary assignments to reduce reconstruction error. We also identify order-dependent error propagation in GPTQ and introduce error decay to attenuate late-stage error accumulation. On Qwen3-14B, QTEA compresses all weights to an effective 1.7 bits per weight while improving average accuracy over the strongest ternary PTQ baseline by 16.7\%. It also achieves 1.40\(\times\) and 2.61\(\times\) lower perplexity on WikiText and C4 respectively. This trend holds on Llama3-8B, where QTEA obtains a 6.6\% accuracy gain and 1.34\(\times\)/1.95\(\times\) lower perplexity on the same datasets. Finally, we develop a lookup-table based kernel that achieves 7.2\(\times\) faster per-token generation over an FP16 baseline. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.00224
PDF
-
Language-Statistical Analysis of Neural Audio Codec Tokens Across Architectures, Corpora, and Noise Conditions
2026-08-31 16:15:36Joonyong Park, Shinnosuke Takamichi, David M. Chan, Shunsuke Kando, Yuki Saito, Hiroshi SaruwatariAbstract
Neural audio codecs (NACs) convert speech into discrete token sequences, and prior work has reported that these sequences follow language-like statistical laws. This paper analyzes the token statistics of 13 NACs spanning multi-codebook residual vector quantization (RVQ), single-codebook VQ, and non-VQ designs, evaluated on three corpora under clean, white-noise, and real-world DEMAND-noise conditions. Zipf and Heaps parameters, unigram entropy, codebook occupancy, and Jensen-Shannon divergence (JSD) are estimated from matched token samples with explicit fit-validity safeguards and family-conditional $n$-gram orders. Corpus identity explains little variance in any metric, whereas acoustic condition and quantizer meta-category dominate in a metric-dependent way, and unigram entropy is the metric most strongly associated with meta-category. Clean-to-noise JSD computed at a common unigram order is associated with mel-cepstral distortion most clearly under DEMAND noise. The collapse and explosion degradation signatures previously reported for RVQ codecs concentrate in RVQ cells under white and DEMAND noise, respectively; explosion also occurs in non-VQ codecs, and single-codebook VQ codecs shift in occupancy and distribution shape without either signature. These results provide architecture-conditioned conventions for applying language-statistical analysis to NAC tokens.
Abstract (translated)
URL
https://arxiv.org/abs/2608.31037
PDF
-
Faithfulness Is Not Free: Auditing Offline KV-Cache Quantization in Retrieval-Augmented Generation
2026-08-31 15:47:23Atta Ul Asad, Ahsan Bilal, Muhammad Ali, Muhammad Haseeb, Dean F. HougenAbstract
Retrieval-augmented generation systems can precompute and store key-value caches of retrieved documents to avoid re-encoding context at every query. Quantizing these caches further reduces storage, but no prior work asks whether compression damages faithfulness, whether responses remain grounded in the retrieved evidence. Faithfulness and accuracy are not equivalent: a model can produce a correct answer that is no longer supported by the context it was given. We evaluate Qwen2.5-7B-Instruct under INT8 and INT4 quantization on RGB and HotpotQA, measuring both accuracy and faithfulness with a hallucination detector, NLI entailment, and an LLM judge. INT8 is near-lossless across both metrics. INT4 reduces accuracy and, more critically, even among answers that remain factually correct, over 90% of faithfulness changes are negative, i.e., accuracy metrics are blind to this regression. The harm grows under noisy retrieval and with more retrieved chunks. Faithfulness must be audited before compressed caches are deployed.
Abstract (translated)
URL
https://arxiv.org/abs/2608.30996
PDF
-
FAMPWQ: Fisher Information-based Adaptive Mixed Precision Weight Quantization for Effective LLM Inference
2026-08-31 15:39:54Gongwei Lee, Ji Liu, Juncheng Jia, Ji WuAbstract
Recent years have witnessed remarkable achievements of Large Language Models (LLMs) in multiple domains, while the excessive resource requirements of LLMs hinder the deployment on resource-constrained devices. Although model quantization stands out as an effective approach, conventional quantization approaches typically incur severe performance degradation due to uniform bit-width or simple heuristic sensitivity evaluation. In this paper, we propose a novel Fisher information-based Adaptive Mixed Precision Weight Quantization approach, i.e., FAMPWQ, which performs layer-adaptive weight quantization for effective LLM inference on commodity GPUs. First, we propose a system model with a novel Fisher information metric to measure the layer-wise sensitivity to quantization. Second, we propose a reinforcement learning-based bit-width allocator in FAMPWQ, which generates an adaptive bit-width allocation strategy based on the Fisher information sensitivity metric. Extensive experiments on 7 models and 5 benchmarks demonstrate that FAMPWQ significantly outperforms 7 baseline approaches in terms of PPL (up to 3.39 smaller), accuracy (up to 6.87% higher), and LLM-as-a-judge comparison (up to 76% win rate).
Abstract (translated)
URL
https://arxiv.org/abs/2608.24945
PDF
-
Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding
2026-08-31 15:13:20Zhigeng Liu, Zhiyuan Ning, Ruixiao Li, Xiaoran Liu, Yuerong Song, Min Zhang, Ziwei He, Xipeng QiuAbstract
The development of long-context Large Language Models (LLMs) is constrained by the memory bandwidth bottleneck and quadratic complexity of the attention mechanism during decoding. To overcome the inherent trade-offs between the memory overhead of metadata-based metrics and the computational inefficiency of adaptive selection strategies, we present Faster Flash Decoding (FFD), a novel hardware-algorithm co-design framework designed to break the memory wall in long-context decoding. FFD integrates the selector and computer into a fully fused kernel, replacing external metadata indices with content-aware scanning via low-bit quantization. Furthermore, we introduce the top-delta strategy, which dynamically filters blocks to achieve distribution-adaptive sparsity without global synchronization. Offering a training-free and plug-and-play solution, FFD also enables the reuse of scanning results for computation, achieving up to 11.6x kernel-level speedup and scaling to 256K context length, with 2.37x end-to-end throughput improvement. Empirical validation on RULER and LongBench confirms that FFD maintains model accuracy while delivering high-ratio sparsity, with code available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2609.00097
PDF
-
NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference
2026-08-31 13:08:15Aur\'elien Lac, Tony WuAbstract
Multimodal models often build on architectures designed for generative vision-language modeling, typically combining separately pretrained vision encoders with causal language models. Visual document retrievers such as ColPali repurpose these models as encoders, carrying over the parameter and compute overhead of a VLM for a non-generative task. We introduce NeoMME, a family of 260M and 800M-parameter Multimodal and Multilingual bidirectional Encoders that process multilingual text and raw image patches in a single bidirectional Transformer encoder. Both models are pretrained from scratch with a masked discrete-diffusion text objective, conditioned on visible image patches for multimodal examples. Both support a 16,384-token context, enough to encode up to two standard 4K UHD images. To demonstrate its downstream capabilities, we fine-tune NeoMME with jointly trained dense and late-interaction heads. On the ViDoRe v3 benchmark, the resulting NeoMME-Retriever 260M outperforms all evaluated models strictly below 800M parameters with 0.523 nDCG@10, while NeoMME-Retriever 800M reaches 0.556. At a matched 2048x2048 image input size on an NVIDIA L40S, NeoMME-260M encodes pages with about 2x the throughput of ColModernVBERT. Hierarchical token pooling and asymmetric quantization compress late-interaction multimodal document embeddings by 255x while preserving over 95% of baseline nDCG@10. We contribute NeoMME to Hugging Face Transformers and release the pretrained backbone and retrieval-compatible checkpoints under Apache 2.0 at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.01657
PDF
-
Q-Strata: Hierarchical Bit Allocation for Mixed-Precision Quantization of Mixture-of-Experts LLMs
2026-08-31 10:39:01Deokjae Lee, Sihun Chu, Hyun Oh SongAbstract
Mixed-precision quantization (MPQ) assigns a different bitwidth to each linear layer of a large language model (LLM) to minimize the quantization-induced quality loss under a fixed budget, but Mixture-of-Experts (MoE) models contain these layers in every expert of every MoE block, so the allocation space grows far larger than in a dense model. Existing methods either allocate within each block under a uniform per-block budget, or allocate across blocks through an additive proxy, and neither directly optimizes a model-level objective over the choices that couple the blocks. We propose Q-Strata, a bi-level allocator that ranks within-block assignments with a cheap proxy and allocates across blocks with a model-level objective evaluated on the assembled quantized model. Its inner stage caches a Pareto frontier of candidates per block over finely spaced budgets, leaving the outer stage to set one budget per block instead of a bitwidth for every linear layer. With the search reduced to one budget per block, the outer stage optimizes this model-level objective directly, capturing the inter-block coupling that additive proxies miss. On Mixtral-8x7B-Instruct, Qwen1.5-MoE-A2.7B, and DeepSeek-V2-Lite, Q-Strata consistently achieves lower WikiText2 perplexity than uniform-bitwidth GPTQ and the state-of-the-art MoE MPQ methods MxMoE and GEMQ in the low-bit regime. The code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.30564
PDF
-
Preference Shapes Relevance: Cross-component Hierarchical Semantic Alignment for Personalized Generative Retrieval
2026-08-31 10:30:22Gaoming Zhang, Angqing Jiang, Jianchun Song, Kena Qi, Dayao Chen, Wei Lin, Defu LianAbstract
Generative Retrieval (GR) has emerged as a promising paradigm by mapping queries directly to Semantic IDs (SIDs) with powerful representation capabilities for candidate items. However, existing SIDs derived solely from item content create a semantic gap, failing to align dynamic query intents with static item representations. Furthermore, current generative paradigms rarely model user behavior sequences and are always bottlenecked by the high inference latency of beam-search autoregressive decoding. To address these challenges, we propose $\textbf{C}$ross-component $\textbf{H}$ierarchical semantic $\textbf{A}$lignment for $\textbf{P}$ersonalized generative retrieval ($\textbf{CHAP}$), a novel personalized GR framework from a hierarchical perspective. First, we design a Hierarchical Semantic Alignment module to align query's latent space with item's quantization path and synchronize multi-granular semantics. Second, we construct a personalized GR framework that models user behavior by synergizing discrete SIDs for structural guidance and continuous representations for fine-grained semantic refinement. Notably, we introduce a Residual Cascading Generation mechanism to restrict the costly multi-step Transformer Decoder to a single-pass inference, boosting inference throughput while mitigating information loss. Extensive experiments on three public datasets, one proprietary industrial dataset, and online A/B tests demonstrate CHAP's superiority, validating the effectiveness and practical value of our approach. The code is publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.30553
PDF
-
Reasoning-Aware Compression: Identifying and Protecting Vulnerable Reasoning Circuits for Energy-Efficient LLM Deployment
2026-08-31 08:36:36Leonard Twagirayezu, Prasenjit MitraAbstract
Large Reasoning Models (LRMs) impose substantial energy costs during deployment, yet current compression methods apply uniform quantization across all components, risking damage to critical reasoning circuits. We present a reasoning-aware compression framework that benchmarks quantization conditions across five reasoning benchmarks, GSM8K, FOLIO, MATH-500, ProofWriter, and MuSiQue, with hardware-level GPU energy measurement; profiles per-module INT4 vulnerability across all 196-224 (layer, projection) pairs via a perturbation sweep on a held-out calibration split, then selectively restores the most sensitive circuits to FP16. Three findings emerge. First, INT4 quantization can increase energy by extending reasoning chains; a 25% power reduction becomes a net energy increase on GSM8K. Second, vulnerability is task-dependent: attention projections are more critical for mathematical reasoning, and sensitivity patterns differ by architecture in logical inference. Third, selective compression achieves Pareto-optimal points inaccessible to uniform methods: R1-Qwen-7B Top-10% on ProofWriter gains +12 pp over FP16 at -9.7% energy, validated on held-out data across five reasoning benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2609.05512
PDF
-
TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information
2026-08-31 07:49:03Dain Kwon, Kanghyun Choi, Hyeyoon Lee, Sunjong Park, Seoyong Lee, Sukjin Kim, Jinho LeeAbstract
Existing GNN quantization methods suffer from considerable quantization overhead, which severely limits their practical usage in real-world scenarios. To this end, we present TopGQ, an accurate post-training GNN quantization framework, alleviating redundant quantization overhead. We propose dual-axis scale absorption, which enables activation quantization along both the outer and inner dimensions by merging one into the adjacency matrix. On top of that, we introduce TopPIN, a proxy for nodes' local structure, and use it to group nodes with similar topology during quantization. Experimental results show that TopGQ reduces quantization time by an order of magnitude while preserving accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2608.30394
PDF
