The Structure of Quantization Damage in LLMs: Why the Next Bit Should Be Spent Globally

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.

Minima-KV: Retention-Preserving KV Cache Compression with Mixed-Format Paged Attention

The key-value (KV) cache is a primary capacity and bandwidth bottleneck in long-context LLM serving. We present Minima-KV, a retention-preserving hierarchy for mixed-format paged attention. Recent and protected Anchor pages remain in FP8, while older non-anchor pages move to packed TQ3; every live-request page remains addressable. Format-specific kernels compute partial attention states and combine them through a globally normalized online-softmax merge, enabling direct heterogeneous decode without a cache-sized dense shadow. Across separate, configuration-bound Qwen3.6-27B profiles on a single 96-GB NVIDIA RTX PRO 6000 Blackwell GPU, deployment accounting reports 18.3 KiB of attention KV per live token, corresponding to 3.50x compression relative to BF16 and 1.75x relative to FP8. A materializing quality profile matches its dense control on 16K RULER needle-in-a-haystack tasks. On the same 503-question LongBench v2 set, measured deltas are -0.80, -0.60, and -0.40 percentage points at 16K, 32K, and 64K. A separate single-pair direct-decode canary with two 59,008-token requests measures 3.625x active-KV compression and 0.9821x throughput relative to its control, routes all 16 full-attention layers without fallback, and retains no dense shadow. These results establish a practical mixed-format path for compressing long-context state without evicting live-request KV pages.

TileMix: Tile-Centric Mixed-Precision Attention for LLM Inference Acceleration

Long-context prefill in large language models (LLMs) incurs substantial computation and memory traffic because dense self-attention computes quadratic query-key scores. Existing methods either use a uniform low-precision path or select token interactions, leaving spatial precision routing over hardware-aligned score tiles outside fused dense attention. We introduce TileMix, a tile-centric precision-routing kernel that makes numerical precision an executable spatial decision over score-tile groups within fused dense attention. TileMix partitions the attention matrix into hardware-aligned score tiles, packs routing decisions into compact bitmasks, and dispatches each tile group through FP16 or INT8 score computation while both paths update a shared online-softmax state. Scalable precision grouping lets each routing bit govern multiple adjacent key tiles, preserving hardware-aligned compute tiles and compact metadata at long contexts. By routing all legal tile groups, TileMix preserves dense token connectivity, requires no training, and supports grouped-query attention, variable-length batches, and INT8 key/value caches. Across LongEval, LV-Eval, and A100 prefill benchmarks on LLaMA, Qwen, and Vicuna, TileMix recovers long-context quality lost under uniform INT8 and improves prefill throughput over FP16, yielding a controllable accuracy-efficiency frontier across model families. The implementation is available at https://github.com/HanzhiZhang-Ulrica/TileMix.

HAMP-LIC: Hessian-Aware Mixed-Precision Post-Training Quantization for Learned Image Compression

Use this plain-text version for the arXiv abstract field: Learned image compression (LIC) models achieve strong rate-distortion performance but are hindered by high computational complexity and encoding-decoding mismatches across heterogeneous hardware platforms. Uniform fixed-precision quantization alleviates these issues but suffers severe quality degradation at low bit widths because it ignores differences in the quantization sensitivities of individual layers. To enable efficient and accurate low-bit deployment of pretrained LIC models, we propose HAMP-LIC, a Hessian-aware mixed-precision post-training quantization (PTQ) framework with a four-stage optimization strategy. First, block-wise sensitivity is estimated from the Hessian trace to capture second-order importance. Second, a task-aware refinement module adjusts these sensitivities by jointly considering quantization distortion and rate-distortion performance. Third, guided by the refined sensitivity profile, bit widths are allocated under a global model-size constraint to balance efficiency and reconstruction quality. Finally, block-wise reconstruction using a small calibration set further suppresses quantization error. Experiments on representative LIC models, including Minnen2018 and Cheng2020, demonstrate that HAMP-LIC achieves up to 4.85x model compression with as little as 0.59% BD-rate loss. It consistently outperforms existing fixed- and mixed-precision PTQ methods across multiple datasets while completely eliminating cross-platform encoding-decoding errors.

NANQ: Noise-Floor-Aware Mixed-Precision Non-Uniform Quantization for Analog Compute-in-Memory

Analog compute-in-memory (CIM) enables energy-efficient neural network inference, but device variation and read noise can severely degrade low-bit quantized models. Existing CIM-oriented quantization methods mainly minimize ideal quantization error, ignoring the hardware noise floor and thus causing inefficient precision allocation. We propose NANQ, a noise-aware mixed-precision non-uniform quantization framework for analog CIM. NANQ models magnitude-dependent weight noise from measured responses of an eFlash CIM array and converts the noise profile into an adaptive quantization density, assigning finer resolution to low-noise regions while avoiding ineffective precision in noise-dominated regions. It further assigns layer-wise bit-widths by identifying each layer's precision saturation point under hardware noise using a unified threshold. On-chip experiments on an eFlash CIM SoC show that, under 2-bit weight-magnitude quantization, NANQ improves vision-model accuracy by 8.05 percentage points and reduces language-model PPL by 54.7% on average over PowerQuant. Mixed-precision NANQ captures most of the gains obtainable from additional quantization resources with only 3.2-3.8 equivalent bits.

MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformers

Post-training quantization (PTQ) has emerged as an effective solution for deploying Vision Transformers (ViTs) on resource-constrained devices. However, existing PTQ methods typically employ uniform bit-widths across transformer components, overlooking their heterogeneous sensitivity to quantization and leading to inefficient precision allocation. In this paper, we propose {MixFrag, a fragility-guided mixed-precision PTQ framework for Vision Transformers. MixFrag first estimates component-level quantization fragility by measuring the Kullback--Leibler (KL) divergence between full-precision and isolated quantized output distributions using a small calibration set. It then formulates bit allocation as a Multiple-Choice Knapsack Problem (MCKP), enabling adaptive layer-wise precision assignment under a target bit budget. Extensive experiments on ImageNet-1K across multiple Vision Transformer architectures demonstrate that MixFrag achieves competitive classification performance under practical mixed-precision settings. Furthermore, evaluations on COCO object detection and instance segmentation show that MixFrag achieves state-of-the-art performance among existing mixed-precision PTQ methods, improving the previous best method by up to 9.6 AP under the challenging MP3/MP3 setting. Additional analyses validate the proposed fragility metric and demonstrate its strong correlation with the learned bit allocation. These results establish MixFrag as an effective framework for mixed-precision post-training quantization of Vision Transformers.

Stable FP4 Training via Transposition-Invariant Block Quantization

Reducing training precision is a key lever for improving the e ciency of large language model (LLM) training, but pushing beyond FP8 to 4-bit oating point (FP4) remains challenging due to instability during optimization. We identify a fundamental source of this instability in existing microscaling approaches: scale inconsistency induced by tensor transposition. In conventional 1D block quantization, forward and backward passes assign di erent scaling factors to the same values after transposition, leading to biased and unstable gradient updates. To address this issue, we propose a low-precision training framework based on 2D block FP4 quantization, which enforces transposition-invariant scaling and preserves consistency between forward and backward computations. We further combine this with truncation-free scaling and stochastic rounding to control quantization error and maintain unbiased gradients. To handle the sensitivity of attention mechanisms, we adopt MXFP8 quantization for query and key projections, yielding a practical mixed-precision design. We evaluate our method on dense LLMs up to 7B parameters and a 30B Mixture-of-Experts model, trained on up to 100B tokens. Across all settings, our approach achieves stable end-to-end FP4 training and closely matches BF16 performance, with less than 1.3% degradation in perplexity and downstream accuracy. These results demonstrate that enforcing forwardbackward scaling consistency is su cient to enable practical FP4 training at scale, providing a simple and e ective pathway toward more e cient LLM training.

MixQuant: Adaptive Mixed-Precision Quantization for Large Language Models

Mixed-precision quantization improves the accuracy of post-training quantization by allocating higher bitwidths to sensitive layers, but existing methods solve the allocation for a single fixed memory budget. In practice the budget varies across deployments and is unknown at calibration time. Adaptive quantization addresses this with one offline calibration that serves any budget, yet current methods score layer sensitivity in a manner that does not consider its dependency on quantization levels of other layers. We show that a layer's sensitivity depends strongly on the bitwidths of its upstream layers and that this dependence shifts the resulting preferred bit allocation. We propose MixQuant, a technique-agnostic adaptive framework that wraps any base quantizer. MixQuant marginalizes each layer's distortion over random quantized upstream configurations to obtain budget-agnostic scores, calibrates the quantizer's parameters on plans the allocator itself produces, and penalizes allocations that leave layers at the lowest bitwidths. A single greedy pass then serves any budget at deployment. Across Llama-3.2-3B, Llama-2-7B, and Mistral-7B under AWQ and GPTQ, MixQuant outperforms adaptive and mixed-precision baselines in every setting, improving average accuracy by up to 8 points and reducing perplexity from 12.43 to 10.70 at the tightest budget, while matching an ILP solver at negligible deployment cost.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference

4-bit quantization enables efficient LLM inference, but suffers from significant accuracy degradation due to outliers. Prior work addresses this problem via data rotation or mixed-precision integer quantization, but often relies on software-managed scaling and frequent dequantization, incurring substantial overhead. Microscaling formats, such as MXINT, eliminate these inefficiencies by encoding scales in hardware, yet remain incompatible with rotation-based methods. Our analysis reveals that outliers vary in severity, from rare extremes to frequent mild deviations, and that quantization sensitivity is unevenly distributed across layers and columns. These insights motivate a fine-grained, sensitivity-guided approach. We introduce MXSens, a training-free method that assigns mixed mantissa bitwidths (4/6/8) based on column- and layer-wise sensitivity, naturally leveraging the block-wise structure of MXINT. MXSens outperforms state-of-the-art quantization methods across a range of models and tasks. Under the W4A4KV4 setting, MXSens achieves perplexities of 3.77 and 7.63 on LLaMA-2-70B and LLaMA-3-8B, respectively, substantially improving over existing baselines on WikiText-2. Our work establishes a new balance between accuracy and resource efficiency for LLM quantization.

ExaGEMM: Exploration Framework for CPU-Driven ML Inference via Associative In-Register Computing for Low-Bit GEMM

Low-bit GEMM is increasingly central to efficient ML inference, yet very-low-bit execution remains a poor fit for conventional CPUs. Practical deployment spans fragmented regimes-from 1/2/4-bit weights to varying activation precision-whose feasibility, reuse opportunity, and support cost differ under fixed SIMD and register-file budgets, making lightweight CPU support selection a first-class design problem. We present ExaGEMM, a workload-aware codesign and exploration framework for CPU-native low-bit GEMM via register-resident LUT execution. The key insight is that existing SIMD datapaths already cover table generation and accumulation; the only new hardware is an in-register select/feed mechanism with explicitly modeled cost. ExaGEMM co-explores parameterized kernels and lightweight SIMD ISA support using analytical models of register feasibility, compute cost, memory traffic, and hardware overhead, pruning the candidate space by 99.2% before simulation. It then identifies non-dominated support points and generates ISA specs, gem5 patches, and GEMM kernels for validation. Across representative ML models and CPU targets, ExaGEMM improves latency by 13.29x over software-only baselines, while showing that workload-aware frontier selection is especially important for mixed-precision LLM workloads.

KronQ: LLM Quantization via Kronecker-Factored Hessian

Post-training quantization (PTQ) is a widely adopted technique for compressing large language models (LLMs) without retraining. Most existing second-order PTQ methods, including GPTQ, construct quantization objectives from input activation statistics, effectively assuming that all output channels contribute equally to the layer-wise reconstruction objective. We propose KronQ, a PTQ framework that challenges this assumption by introducing the gradient covariance into the quantization pipeline. Under the Kronecker-factored Hessian approximation, the quantization loss depends jointly on both the activation and gradient covariances, and KronQ exploits this at two complementary levels. (1) KronQ introduces bidirectional incoherence processing, extending the existing input-side random rotation to the output dimension using the gradient covariance, reducing weight magnitude variance across both input and output dimensions. (2) KronQ derives a new sensitivity metric for inter-layer mixed-precision allocation, driven by the gradient and activation Hessian traces. Notably, in the case of 2-bit weight-only quantization on LLaMA-3-70B, while GPTQ and GPTAQ diverge or produce degenerate quantizations (>2000 perplexity on WikiText-2), \KronQ{} achieves 7.93 perplexity.

RotateAttention: RoPE-Aware Rotation and Range Rectification for INT4 Quantized Attention in Video Generation

In $\textbf{DiT-based video generation models equipped with 3D Rotary Position Embeddings (3D RoPE)}$, the attention mechanism remains a primary computational bottleneck due to its quadratic complexity with respect to sequence length. While quantized $\textbf{FlashAttention}$ offers a promising path toward hardware acceleration, existing low-bit quantization methods overlook two critical challenges in this setting: $\textbf{1)}$ applying online rotation matrices -- a widely used technique for mitigating outliers in Queries ($Q$) and Keys ($K$) -- is difficult to reconcile with $\textbf{RoPE}$; and $\textbf{2)}$ the non-negative attention matrix $P = \exp(QK - \max(QK))$ makes symmetric quantization waste half of the 4-bit dynamic range. In this work, we observe that the outlier distributions of $Q$ and $K$ are strongly affected by the dimensional partitioning of $\textbf{3D RoPE}$. Based on this finding, we propose $\textbf{RotateAttention}$, an efficient $\textbf{mixed-precision INT4 FlashAttention}$ framework tailored for $\textbf{DiT-based video generation models with 3D RoPE}$, using selective $\textbf{FP16 fallback}$ for accuracy-sensitive attention blocks and denoising steps. RotateAttention introduces two core techniques: $\textbf{1) RoPE-aware Rotation}$, which employs either mergeable rotation matrices that can be fused into RoPE or negligible-overhead matrices to mitigate RoPE-induced outliers in $Q$ and $K$; and $\textbf{2) Range-optimized $P$ Quantization}$, which uses fixed scales and zero-points to fully exploit the $\textbf{INT4 numerical range}$ with minimal computational overhead. Experiments show that $\textbf{RotateAttention}$ preserves video generation quality nearly identical to full-precision baselines while achieving up to 1.68$\times$ end-to-end speedup and 2.2$\times$ kernel-level acceleration.

SEADA: An efficient methodology for optimizing mixed-precision DNNs on multi-precision spatial architectures

Mixed-precision computation has been introduced in deep neural networks (DNNs) as an effective approach to reduce latency, energy consumption, and memory footprint. However, efficiently mapping mixed-precision networks onto multi-precision spatial architectures poses several challenges. These include determining the appropriate precision for each layer, balancing layer-wise accuracy sensitivity to quantization against architectural heterogeneity and system-level constraints, and accurately estimating the system-level cost of heterogeneous precision assignments. This work presents SEADA, an efficient methodology designed to address these challenges. SEADA comprises: (i) a configurable system-level analytical cost model of a multi-precision spatial accelerator architecture; (ii) a fast mapping tool that identifies near-optimal mappings of DNN workloads onto the target integer accelerator; (iii) analytical models for floating-point layers to estimate the overall benefits of mixed-precision execution; and (iv) a per-layer precision selection methodology based on bit-level entropy, enabling efficient assignment across multiple numerical precisions. SEADA's efficiency provides designers with a robust framework for the design-space exploration of multi-precision architectures.

Operator-Aware Mixed-Precision Tolerance Calibration for Tensor Kernels

Most tensor-kernel correctness tests go through a fixed-shape all close-style check with hand-picked absolute and relative tolerances. The thresholds are copied across the corpus and rarely revisited. We mine the element-wise error distribution of every test case from accumulated cloud GPU runs across the 26-entry gpuemu corpus and 2 dtypes (8,076 result rows). We then ask one empirical question: what absolute tolerance would the kernel itself, observed under its correct implementation, justify? The answer is much tighter than the current hand-picked atol. The largest tightening is attention_triton fp16 at $2{,}184\times$. Restricted to the seven LLM-style buggy variants for which the corpus ships a paired correct counterpart, calibrated per-(op, dtype) tolerances raise bug-detection recall from 73.2% (1,805 of 2,467) to 82.4% (2,034 of 2,467), an absolute gain of 9.3 percentage points (+229 new detections). The control false-positive count rises from 0 to 20 out of 1,882 correct-control cases (+1.1 percentage points).

MosaicQuant: Inlier-Outlier Disaggregation for Unified 4-Bit LLM Quantization

4-bit quantization significantly reduces the memory footprint and accelerates the inference of large language models (LLMs). However, its limited bit-width representation struggles to faithfully capture both dense common values (\emph{inliers}) and rare large-magnitude values (\emph{outliers}), causing substantial accuracy degradation. Existing mixed-precision methods mitigate this by retaining outliers in high precision, but at the cost of breaking the uniformity of low-bit execution, introducing precision conversion and extra data movement that undermine practical speedup. We propose \textbf{MosaicQuant}, a unified 4-bit LLM quantization paradigm built on a novel principle of \emph{inlier--outlier disaggregation}. Rather than elevating outlier precision, MosaicQuant quantizes the full weight matrix into a dense 4-bit base component, where inliers are captured faithfully while outlier are inevitably quantized. A sparse 4-bit residual component is then introduced to compensate for these quantization errors, selectively targeting the most error-critical weight blocks where output distortion is shown to be concentrated. However, a unified representation alone is insufficient, as naïvely executing the sparse residual as a separate kernel still breaks the unified low-bit inference pipeline. To bridge this gap, we introduce \textbf{ZipperEngine}, which fuses sparse block computation into the dense 4-bit GEMM kernel via an overlapped pipeline, unifying not only the representation but also the execution into a single coherent low-bit inference pipeline. Extensive experiments on LLaMA3 and Qwen3 demonstrate that MosaicQuant preserves near-FP16 accuracy while achieving up to $1.24\times$ speedup over the W16A16 baseline.

Quantizing Time-Series Models As Dynamical Systems: Trajectory-Based Quantization Sensitivity Score

We introduce the Trajectory-based Quantization Sensitivity Score (TQS), a metric that reframes post-training quantization (PTQ) through the lens of dynamical-systems stability. By modeling the network's rollout as a discrete-time dynamical system, TQS characterizes how quantization-induced errors propagate and amplify over the rollout horizon. Unlike conventional PTQ methods, where sensitivity analysis is often coupled to the quantization procedure, TQS enables a priori sensitivity estimation decoupled from quantizer selection and bit-width assignment. This separation allows for quantization budget planning even for black-box or compiled networks with fused operators. Building on this, we present TQS-PTQ, a flexible mixed-precision framework that requires no calibration data or costly second-order approximations. Our experiments show that a dynamical-systems perspective provides a robust, high-performing pathway for low-precision deployment in resource-constrained settings.

DynamicPTQ: Mitigating Activation Quantization Collapse via Residual-Stream Dynamics

Post-training quantization (PTQ) is essential for efficient large language model inference, but reliably quantizing activations remains challenging when weights, activations, and KV caches are all quantized to 4-bit precision. A key difficulty lies in massive activations, whose extreme values dominate the activation range and amplify quantization errors. State-of-the-art methods mainly mitigate massive activations through transformation-based smoothing, such as orthogonal rotations and affine scaling, but overlook the cross-layer dynamics of the residual stream. In this paper, we show that massive activations emerge and disappear in a phase-wise pattern across network depth, triggering large residual changes. These changes cause newly injected layer-wise updates to dominate the 4-bit quantization scale and weaken historical residual information. To characterize this behavior, we introduce Jump Ratio and Historical Feature SNR. This suggests that static transformation-based smoothing cannot fully resolve dynamic quantization instability caused by cross-layer residual changes. Based on this analysis, we propose DynamicPTQ, a Dynamic Post-Training Quantization policy for phase-aware mixed-precision activation quantization. DynamicPTQ identifies quantization-sensitive layers from residual-stream dynamics and assigns 8-bit activation precision only to these layers, while keeping weights, KV caches, and other activations in 4-bit precision. It can be directly integrated with strong PTQ baselines such as QuaRot, SpinQuant, and FlatQuant. Experiments on LLaMA-2 and LLaMA-3 show that DynamicPTQ consistently improves perplexity and zero-shot QA performance under W4A4KV4 quantization, while achieving 1.05 to 1.07 times throughput improvement with modest memory overhead. These results demonstrate a practical path toward robust low-bit LLM inference.

TileFuse: A Fused Mixed-Precision Kernel Library for Efficient Quantized LLM Inference on AMD NPUs

With the growing demand for on-device LLM inference, edge SoCs increasingly integrate NPUs to improve performance and energy efficiency under tight power and thermal budgets. However, practical LLM deployment on current client NPUs remains difficult: widely used quantization formats such as AWQ do not map cleanly onto many existing NPU software stacks, which are often proprietary and expose limited low-level control. In this work, we present TileFuse, a close-to-metal mixed-precision kernel library for AMD XDNA2 NPUs that targets GEMM/GEMV-based operators in quantized LLM inference. TileFuse brings practical low-bit formats such as AWQ-style W4A16 and W8A16 directly onto XDNA2, rather than forcing the model to be reshaped around an NPU-specific quantization scheme. TileFuse co-designs weight layout, metadata placement, mixed-precision microkernels, and array-level dataflow. Specifically, it fuses unpacking, dequantization, and GEMM/GEMV execution into a single kernel flow, introduces an interleaved pre-tiling layout that supports GEMM dimensions up to 32K, and redesigns GEMV dataflow to utilize the full 4x8 AIE array. Across kernel-level evaluations, TileFuse improves performance by up to 121.6% for GEMM and 281% for GEMV over full-precision baselines, while delivering more than 2x performance and energy-efficiency gains over strong iGPU baselines on GEMM. In end-to-end LLM experiments on Ryzen AI laptops, TileFuse achieves up to 2.0x lower prefilling latency with more than 64.6% lower energy consumption. Together, these results show that XDNA2 is a practical target for AWQ-style edge LLM inference and that native NPU support for off-the-shelf quantization can make NPUs substantially more usable in real client deployments.

SpectrumKV: Per-Token Mixed-Precision KV Cache Transfer for Prefill-Decode Disaggregated LLM Serving

Prefill-decode (PD) disaggregation decouples prompt processing from token generation, but it also turns the key-value (KV) cache into a network payload. Existing PD-side KV reduction methods are mostly binary: selected tokens are transmitted at full precision and the rest are not transmitted. This paper argues that binary selection leaves a useful design space unused. SpectrumKV assigns a precision level to each token instead: attention sinks and other high-importance tokens are protected at FP16, medium-importance tokens are sent at INT8, and low-importance tokens are sent at INT4 when the model can tolerate it. The main practical complication is that INT4 tolerance is model-dependent. Qwen2.5-7B catastrophically fails under INT4 KV quantization, while Mistral-7B and Gemma-2-9B remain stable. SpectrumKV therefore runs a lightweight deployment-time probe: three aggressive NIAH trials under a 3-tier policy. Models that pass use FP16+INT8+INT4; models that fail fall back to FP16+INT8. Across Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3, and Gemma-2-9B-it, SpectrumKV improves quality at the same transfer budget. At a 50% normalized KV budget on WikiText-2, SpectrumKV changes perplexity by +1.97%,-0.06%, and-0.44%, respectively, compared with PDTrim's +25.85%, +22.07%, and +35.63%. On NIAH retrieval at 4096 tokens, the adaptive policy reaches 52.6% on Qwen at the aggressive b=0.3 budget versus 26.3% for PDTrim, and reaches 100% by b=0.5; Mistral and Gemma preserve retrieval under the 3-tier policy. End-to-end GPU timing of the transfer path shows 50-62% TTFT reductions at b=0.5. These results suggest that PD KV transfer should be treated as a precision-allocation problem, not only as token pruning.

QuBLAST: A Framework for Quantizing Large Language Models with Block-Level Compression Approach and Activation Scaling Strategy

LLMs have become the state-of-the-art algorithms for solving NLP tasks. However, they typically come at huge computational and memory costs, thus making them difficult to deploy on embedded systems. Toward this, state-of-the-art methods typically employ uniform post-training quantization (PTQ) across attention blocks of the network, hence overlooking the potential of applying different quantization levels in the same network. They also employ complex operations to mitigate the negative impact of activation outliers, hence incurring high computational overheads. Moreover, they have not considered evaluation using emerging LLMs with non-conventional attention architectures (e.g., state-space models), which pose different challenges in applying quantization. To address these limitations, we propose QuBLAST, a novel PTQ methodology that employs block-level compression approach with activation scaling strategy for LLMs. Block-level compression approach enables mixed-precision quantization across blocks of the network, while activation scaling strategy efficiently mitigates the negative impact of activation outliers. Specifically, QuBLAST first analyzes the sensitivity of different attention blocks in the pre-trained model through the cross-entropy loss analysis. QuBLAST leverages this sensitivity analysis to determine the weight quantization level for each attention block in the model. Furthermore, QuBLAST employs the activation scaling map for each block to control the range of activation values and mitigate the negative impact of activation outliers, thereby enabling better quantization results. Experimental results show that, QuBLAST reduces model sizes by 40%-45.2% across different model architectures (i.e., Qwen3-8B, Llama3-8B, Mistral v0.1-8B, and Falcon H1R-7B), while maintaining the performance within 5% perplexity increase for the WikiText-2 and WikiText-103 datasets.

dMX: Differentiable Mixed-Precision Assignment for Low-Precision Floating-Point Formats

Quantizing large language models (LLMs) to low-precision floating-point representations is central to efficient deployment, yet applying a single bit-width uniformly across all layers is sub-optimal in terms of both performance and accuracy. This work introduces dMX, a differentiable mixed-precision quantization framework for learnable floating-point bit-width assignment. We study its application for the microscaling floating-point (MXFP) family of data types defined by the Open Compute Project (OCP) standard. The per-layer bit-width assignment is formulated as a continuous optimization problem in which each layer's floating-point format format is parameterized by a scalar parameter, folding the multi-variate design space into a single learnable offset. During training this offset takes continuous values, avoiding sudden oscillations between discrete quantization formats. A temperature-based annealing schedule progressively discretizes the learned offsets, ensuring that the final configuration maps to hardware-compatible MXFP formats without abrupt transitions between training and inference behavior. A target-aware regularization term steers the average bit-width toward a user-specified budget, serving as a coarse-grained proxy for inference cost and balancing model quality against deployment efficiency. We performed experiments on different families of LLM, such as Llama, Qwen3, and SmolLM2, evaluating perplexity on WikiText-2 and accuracy on four zero-shot reasoning benchmarks. Across these settings, dMX consistently yields Pareto-dominating models and improves over Kullback-Leibler (KL) divergence-based layer-selection heuristics, efficiently navigating trade-offs between model quality and average bit-width.

WindowQuant: Mixed-Precision KV Cache Quantization based on Window-Level Similarity for VLMs Inference Optimization

Recently, video language models (VLMs) have been applied in various fields. However, the visual token sequence of the VLM is too long, which may cause intolerant inference latency and GPU memory usage. Existing methods propose mixed-precision quantization to the key-value (KV) cache in VLMs based on token granularity, which is time-consuming in the search process and hardware inefficient during computation. This paper introduces a novel approach called WindowQuant, which employs window-adaptive mixed-precision quantization to optimize the KV cache. WindowQuant consists of two modules: window-level quantization search and window-level KV cache computation. Window-level quantization search quickly determines the optimal bit-width configuration of the KV cache windows based on the similarity scores between the corresponding visual token windows and the text prompt, maintaining the model accuracy. Furthermore, window-level KV cache computation reorders the KV cache windows before quantization, avoiding the hardware inefficiency caused by mixed-precision quantization in inference computation. Extensive experiments demonstrate that WindowQuant outperforms state-of-the-art VLM models and KV cache quantization methods on various datasets.

CoQuant: Joint Weight-Activation Subspace Projection for Mixed-Precision LLMs

Post-training quantization (PTQ) has become an important technique for reducing the inference cost of Large Language Models (LLMs). While recent mixed-precision methods improve ultra-low bit quantization by preserving critical subspaces in high precision, they typically construct these subspaces relying solely on activation statistics. This ignores the fundamental nature of linear operations, where the output perturbation is jointly driven by both activation and weight quantization noise. In this paper, we propose CoQuant, a joint weight-activation subspace projection method. By theoretically modeling the expected output error, CoQuant formulates a closed-form weighted PCA solution that balances activation and weight covariances to select the optimal high-precision subspace. Extensive experiments on Llama-3.2 and Qwen2.5 models show that CoQuant consistently outperforms strong PTQ baselines in both WikiText perplexity and zero-shot common-sense reasoning accuracy. These results demonstrate that joint weight-activation subspace modeling provides a principled and effective direction for low-bit LLM quantization. The source code is available at https://github.com/Zachary5895/CoQuant.