arXiv subjects

Dan Alistarh

Publications and source records attributed to Dan Alistarh.

At least 19 recordsLinked to original sources

arXiv2026

Disaggregated Quantization: Specializing LLM Prefill and Decode

Prefill and decode reward different approaches to quantization: low-precision arithmetic accelerates prompt processing, while compact weights reduce memory traffic during generation. We propose "disaggregated quantization" (DQ), which specializes computation formats, weights and storage placement to both of these phases. On Qwen 3 and Gemma 3, removing activation quantization specifically on decode improves accuracy on decode-heavy tasks without increasing inference cost. Training separate compute-native prefill weights accelerates prompt processing relative to weight-only inference while matching or exceeding its accuracy at 2-3-bit decode on both decode-heavy and prefill-heavy tasks. With released Qwen3.8-27B GGUF decoders, training an NVFP4 prefiller improves 1-bit accuracy by 32.5 points on MMLU-Pro and 35.3 on MMMU-Pro without modifying the decode checkpoint. To accommodate the additional checkpoint on a single device, offloaded disaggregated prefill (ODP) streams its weights from SSD, amortizing loading over prompt length. On the same 27B model, ODP delivers a 1.78x time-to-first-token speedup over the weight-only baseline at 8K prompt length in llama.cpp. We evaluate accuracy under disaggregated serving in vLLM and further validate shared-weight format disaggregation through post-training quantization on models up to 2.8T parameters.

cs.LG↗

arXiv2026

Statistically-Lossless Quantization of Large Language Models

Model quantization has become essential for efficient large language model deployment, yet existing approaches present clear trade-offs: methods such as GPTQ and AWQ achieve practical compression but are lossy, while lossless techniques preserve fidelity but lack inference acceleration. This paper explores the middle ground of statistically-lossless compression, examining three complementary aspects of what losslessness means for quantized LLMs. First, task-lossless compression preserves zero-shot benchmark accuracy within natural sampling variance and is achievable at aggressive bitwidths. Second, we formalize the stricter notion of distribution-lossless compression, requiring the quantized model's next-token distribution to be practically indistinguishable from the original, and propose the Expected Acceptance Rate (EAR), the maximum token-agreement probability under optimal coupling, as a directly interpretable fidelity metric. For example, EAR >= 0.99 means 99% agreement. Third, we prove a gamma-squared variance law showing that symmetric quantization inflates noise variance by gamma^2 relative to asymmetric quantization, making asymmetric quantization a prerequisite for distribution-lossless fidelity but not for task-level preservation. Through SLQ, a layer-wise non-uniform method with asymmetric quantization and wide bitwidth search, we obtain task-lossless compression at well below 4 bits per parameter, as low as 3.3 bits depending on the model, distribution-lossless compression at 5-6 bits per parameter on average, and inference speedups of 1.7-3.7x compared to FP16 using optimized kernels. Source code is available at [https://github.com/IST-DASLab/SLQ](https://github.com/IST-DASLab/SLQ).

cs.LG↗

arXiv2026

The Sparsity Whisperer

Pruning reduces the inference cost of large language models, but existing criteria primarily preserve large activations or reconstruct layer outputs. We argue that this overlooks a key computation performed by particularly sparsity-sensitive neurons in the MLP up and gate projections: separating similar inputs into dissimilar outputs. This suggests that effective pruning should preserve not only activations, but also the differences between outputs more broadly. We introduce a family of difference-informed pruning methods built upon this principle. Wisp is a first-order, update-free method that scores weights using input-difference norms, and Wisp+ refines this score neuronwise using the input pairs each neuron separates most strongly. Finally, Whisper is a second-order method that uses a lightly regularized difference Hessian as its reconstruction objective. Across Llama 2 and 3.1 models from 7B to 405B parameters, our second-order variant consistently improves over strong reconstruction-based baselines, while our update-free variants improve over activation-aware baselines, especially in constrained settings. The improvements over Wanda and SparseGPT extend to structured sparsity, downstream evaluations, and other model families. Augmenting stronger techniques such as RIA and ALPS with our difference-informed criteria yields further improvements, shifting the overall accuracy-runtime frontier outward at negligible additional cost. These results suggest that preserving output differences is a broadly useful and composable signal for post-training LLM sparsification.

cs.LG↗

arXiv2026

GPTQ-2D: Cubic-Time Two-Sided Adaptive Rounding

Adaptive rounding methods such as GPTQ, or equivalently Babai's nearest plane algorithm, round a real matrix to integers under a quadratic metric. They process the entries in a fixed order, one at a time, propagating each rounding error to the entries not yet processed through a triangular feedback matrix. We study the two-sided version of this task, in which fixed nonsingular basis matrices act on both the left and the right of the residual; the familiar one-sided case is the special case of an identity right basis. Vectorizing the matrix turns the two-sided objective into a quadratic metric whose Gram matrix is a Kronecker product, so the one-dimensional algorithm applies verbatim, but takes quartic time in the matrix dimension. We present GPTQ-2D, which produces the identical rounded matrix in cubic time. It rounds the entries anti-diagonal by anti-diagonal; entries on the same anti-diagonal are independent and are rounded in parallel.

cs.DS↗

arXiv2026

DarwinLM: Evolutionary Structured Pruning of Large Language Models

Large Language Models (LLMs) have achieved significant success across various NLP tasks. However, their massive computational costs limit their widespread use, particularly in real-time applications. Structured pruning offers an effective solution by compressing models and directly providing end-to-end speed improvements, regardless of the hardware environment. Meanwhile, different components of the model exhibit varying sensitivities towards pruning, calling for non-uniform model compression. However, a pruning method should not only identify a capable substructure, but also account for post-compression training. To this end, we propose DarwinLM, a method for training-aware structured pruning. DarwinLM builds upon an evolutionary search process, generating multiple offspring models in each generation through mutation, and selecting the fittest for survival. To assess the effect of post-training, we incorporate a lightweight, multistep training process within the offspring population, progressively increasing the number of tokens and eliminating poorly performing models in each selection stage. We validate our method through extensive experiments on Llama-2-7B, Llama-3.1-8B and Qwen-2.5-14B-Instruct, achieving state-of-the-art performance for structured pruning. For instance, DarwinLM surpasses ShearedLlama while requiring 5x less training data during post-compression training. Code is at: https://github.com/IST-DASLab/DarwinLM

cs.LG↗

arXiv2026

One Simple Trick for Improving the Performance of Energy-Limited Local Inference and Training

Energy supply and heat dissipation are two of the main challenges with modern GPU deployments. While typically discussed in the context of new datacenter constructions, the same constraints also apply to small form-factor consumer devices, such as the DGX spark. In workloads characterized by alternating compute-intensive tasks such as matmuls with memory-bound operations such as norms or cross-entropy, the compute-intensive parts might hit power and/or thermal limits and start throttling. In this short paper, we show that chunking the workload into smaller parts that alternate compute and memory in higher frequencies, these power and temperature spikes can be smoothed out, preventing throttling and resulting in considerably faster wall-clock time and reduced total energy consumption. We present several scenarios in which this effect can be exploited on a DGX Spark with up to 2% performance and energy improvements, and demonstrate that the same phenomenon also happens on less constrained systems, such as a multi-GPU server, albeit at significantly reduced effect size of 1-2%.

cs.PF↗

arXiv2026

DASH: Faster Shampoo via Batched Block Preconditioning and Efficient Inverse-Root Solvers

Shampoo is one of the leading approximate second-order optimizers: a variant of it has won the MLCommons AlgoPerf competition, and it has been shown to produce models with lower activation outliers that are easier to compress. Yet, applying Shampoo currently comes at the cost of significant computational slowdown, due to its expensive internal operations. In this paper, we take a significant step to address this shortcoming by proposing \method (for \textbf{D}istributed \textbf{A}ccelerated \textbf{SH}ampoo), a faster implementation of Distributed Shampoo based on two main new techniques: First, we show that preconditioner blocks can be stacked into 3D tensors to significantly improve GPU utilization; second, we introduce the Newton-DB iteration and the Chebyshev polynomial approximations as novel and faster approaches for computing the inverse matrix roots required by Shampoo. Along with these algorithmic contributions, we provide a first in-depth analysis of how matrix scaling critically affects Shampoo convergence. On the practical side, our GPU-aware implementation achieves up to $5.6\times$ faster optimizer steps compared to the well-optimized Distributed Shampoo, while Newton-DB attains the lowest validation perplexity per iteration among all tested methods. Our code is available at https://github.com/IST-DASLab/DASH.

cs.LG↗

arXiv2026

CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training

Despite significant work on low-bit quantization-aware training (QAT), there is still an accuracy gap between such techniques and native training. To address this, we introduce CAGE (Curvature-Aware Gradient Estimation), a new QAT method that augments the straight-through estimator (STE) gradient with a curvature-aware correction designed to counteract the loss increase induced by quantization. CAGE is derived from a multi-objective view of QAT that balances loss minimization with the quantization constraints, yielding a principled correction term that depends on local curvature information. On the theoretical side, we introduce the notion of Pareto-optimal solutions for quantized optimization, and establish that CAGE yields strong convergence guarantees in the smooth non-convex setting. In terms of implementation, our approach is optimizer-agnostic, but we provide a highly-efficient implementation that leverages Adam statistics. CAGE significantly improves upon the prior state-of-the-art methods in terms of accuracy, for similar computational cost: for QAT fine-tuning, it halves the compression accuracy loss relative to the prior best method, while for QAT pre-training of Llama models, its accuracy for 3-bit weights-and-activations (W3A3) matches the accuracy achieved at 4-bits (W4A4) with the prior best method. The official implementation can be found over https://github.com/IST-DASLab/CAGE .

cs.LG↗

arXiv2026

LoRDO: Distributed Low-Rank Optimization with Infrequent Communication

Distributed training of foundation models via $\texttt{DDP}$ is limited by interconnect bandwidth. While infrequent communication strategies reduce synchronization frequency, they remain bottlenecked by the memory and communication requirements of optimizer states. Low-rank optimizers can alleviate these constraints; however, in the local-update regime, workers lack access to the full-batch gradients required to compute low-rank projections, which degrades performance. We propose $\texttt{LoRDO}$, a principled framework unifying low-rank optimization with infrequent synchronization. We first demonstrate that, while global projections based on pseudo-gradients are theoretically superior, they permanently restrict the optimization trajectory to a low-rank subspace. To restore subspace exploration, we introduce a full-rank quasi-hyperbolic update. $\texttt{LoRDO}$ achieves near-parity with low-rank $\texttt{DDP}$ in language modeling and downstream tasks at model scales of $125$M--$720$M, while reducing communication by $\approx 10 \times$. Finally, we show that $\texttt{LoRDO}$ improves performance even more in very low-memory settings with small rank/batch size.

cs.LG↗

arXiv2026

Apertus LLM Family Expansion via Distillation and Quantization

The wide adoption of LLMs has led to their use in great variety of applications and scenarios, such as chatbot assistants and data annotation, creating the need for the models to satisfy certain budget and hardware constraints. This has led to the trend of LLMs being released in batches consisting of similar models of various sizes for the family of models to adhere to as wide of a range of constraints as possible. In this paper, we validate distillation and quantization as a cost-effective way to expand model families to new sizes and hardware formats. Based on the open-recipe Apertus 8B LLM, we produce Apertus-v1.1 - a distilled family of models with up to 4B parameters trained on 1.7T permissive license tokens. We demonstrate cost-efficiency and strong accuracy performance of our approach for covering large ranges of hardware and systems requirements.

cs.LG↗

arXiv2026

Expand Neurons, Not Parameters

This work demonstrates how increasing the number of neurons in a network without increasing its total number of non-zero parameters improves performance. We show that this gain corresponds with a decrease in interference between multiple features that would otherwise share the same neurons. On symbolic Boolean tasks, splitting each neuron into sparser sub-neurons with knowledge of the clauses systematically reduces polysemanticity metrics and yields higher task accuracy. Notably, even random splits of neuron weights approximate these gains, indicating that reduced collisions, not precise assignment, are a primary driver. Consistent with the superposition hypothesis, the benefits of this framework grow with increasing interference: when polysemantic load is high, accuracy improvements are the largest. Transferring these insights to more realistic models, including classifiers over CLIP embeddings, convolutional neural networks, and deeper multilayer networks, we find that widening networks while maintaining a constant non-zero parameter count consistently increases accuracy. These results identify an interpretability-grounded mechanism to leverage width against superposition, improving performance without increasing the number of non-zero parameters. Such a direction is well matched to modern accelerators, where memory movement of non-zero parameters, rather than raw compute, is often a dominant bottleneck.

cs.LG↗

arXiv2026

Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation

The NVFP4 lower-precision format, supported in hardware by NVIDIA Blackwell GPUs, promises to allow, for the first time, end-to-end fully-quantized pre-training of massive models such as LLMs. Yet, existing quantized training methods still sacrifice some of the representation capacity of this format in favor of more accurate unbiased quantized gradient estimation by stochastic rounding (SR), losing noticeable accuracy relative to standard FP16 and FP8 training. In this paper, improve the state of the art for quantized training in NVFP4 via a novel unbiased quantization routine for micro-scaled formats, called MS-EDEN, that has more than 2x lower quantization error than SR. We integrate it into a novel fully-NVFP4 quantization scheme for linear layers, called Quartet II. We show analytically that Quartet II achieves consistently better gradient estimation across all major matrix multiplications, both on the forward and on the backward passes. In addition, our proposal synergizes well with recent training improvements aimed specifically at NVFP4. We further validate Quartet II on end-to-end LLM training with up to 1.9B parameters on 38B tokens. We provide kernels for execution on NVIDIA Blackwell GPUs with up to 4.2x speedup over BF16. Our code is available at https://github.com/IST-DASLab/Quartet-II .

cs.LG↗

arXiv2026

WUSH: Near-Optimal Adaptive Transforms for LLM Quantization

Quantizing LLM weights and activations is a standard approach for efficient deployment, but a few extreme outliers can stretch the dynamic range and amplify low-bit quantization errors. Prior transform-based mitigations (e.g., Hadamard rotations) are fixed and data-agnostic, and their optimality for quantization has remained unclear. We derive closed-form optimal linear blockwise transforms for joint weight-activation quantization under standard RTN AbsMax-scaled block quantizers, covering both integer and floating-point formats. The resulting construction, WUSH, combines a Hadamard backbone with a data-dependent second-moment component to form a non-orthogonal transform that is provably near-optimal for FP and INT quantizers under mild assumptions while admitting an efficient fused GPU implementation. Empirically, WUSH improves W4A4 accuracy over the strongest Hadamard-based baselines (e.g., on Llama-3.1-8B-Instruct in MXFP4, it gains +2.8 average points with RTN and +0.7 with GPTQ) while delivering up to 5.8$\times$ per-layer throughput over BF16 via FP4 MatMul. Source code is available at https://github.com/IST-DASLab/WUSH.

cs.LG↗

arXiv2026

"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization

Quantization is a powerful tool for accelerating large language model (LLM) inference, but the accuracy-performance trade-offs across different formats remain unclear. In this paper, we conduct the most comprehensive empirical study to date, evaluating FP8, INT8, and INT4 quantization across academic benchmarks and real-world tasks on the entire Llama-3.1 model family. Through over 500,000 evaluations, our investigation yields several key findings: (1) FP8 (W8A8-FP) is effectively lossless across all model scales, (2) well-tuned INT8 (W8A8-INT) achieves surprisingly low (1-3\%) accuracy degradation, and (3) INT4 weight-only (W4A16-INT) is more competitive than expected, rivaling 8-bit quantization. Further, we investigate the optimal quantization format for different deployments by analyzing inference performance through the popular vLLM framework. Our analysis provides clear deployment recommendations: W4A16 is the most cost-efficient for synchronous setups, while W8A8 dominates in asynchronous continuous batching. For mixed workloads, the optimal choice depends on the specific use case. Our findings offer practical, data-driven guidelines for deploying quantized LLMs at scale -- ensuring the best balance between speed, efficiency, and accuracy.

cs.LG↗

arXiv2026

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling

Quantization has become a standard tool for efficient LLM deployment, especially for local inference, where models are now routinely served at 2-3 bits per parameter. The state of the art is currently split into simple scalar quantization techniques, such as GPTQ or AWQ, which are widely deployed but plateau in accuracy at 3-4 bits per parameter (bpp), and "second-generation" vector- or trellis-quantized methods, such as QTIP, GPTVQ and AQLM, which push the accuracy frontier but are notoriously hard to implement and to scale. In this paper, we ask whether this gap is fundamental, or whether a carefully optimized $\textit{scalar}$ quantizer can recover most of it. We answer in the affirmative, by introducing GSQ (Gumbel-Softmax Quantization), a post-training scalar quantization method which jointly learns the per-coordinate grid assignments and the per-group scales using a Gumbel-Softmax relaxation of the discrete grid. GSQ matches the cardinality of the relaxation to the small number of levels available in the target bit-width regime (e.g., 3-8 levels for ternary and 3 bpp, respectively), making optimization tractable. Practically, on the standard Llama-3.1-8B/70B-Instruct models, GSQ closes most of the gap between scalar quantization and the QTIP frontier at 2 and 3 bits, while using a symmetric scalar grid with group-wise quantization, and thus remains compatible with existing scalar inference kernels. We further show that the same discrete-assignment optimization can be applied to practical GGUF K-Quant checkpoints: starting from publicly released GGUF models, GSQ improves accuracy while projecting the result back into the same deployment format. Finally, GSQ scales to trillion-scale Mixture-of-Experts models such as Kimi-K2.5, where vector-quantized methods are difficult to apply. The source code is publicly available at https://github.com/IST-DASLab/GSQ.

cs.CL↗

arXiv2026

The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm

Quantizing the weights of large language models (LLMs) from 16-bit to lower bitwidth is the de facto approach to deploy massive transformers onto more affordable accelerators. While GPTQ emerged as one of the standard methods for one-shot post-training quantization at LLM scale, its inner workings are described as a sequence of algebraic updates that obscure geometric meaning or worst-case guarantees. In this work, we show that, when executed back-to-front (from the last to first dimension) for a linear layer, GPTQ is mathematically identical to Babai's nearest plane algorithm for the classical closest vector problem (CVP) on a lattice defined by the Hessian matrix of the layer's inputs. This equivalence is based on a sophisticated mathematical argument, and has two analytical consequences: first, the GPTQ error propagation step gains an intuitive geometric interpretation; second, GPTQ inherits the error upper bound of Babai's algorithm under the assumption that no weights are clipped. Leveraging this bound, we design post-training quantization methods that avoid clipping, and outperform the original GPTQ. In addition, we provide efficient GPU inference kernels for the resulting representation. Taken together, these results place GPTQ on a firm theoretical footing and open the door to importing decades of progress in lattice algorithms towards the design of future quantization algorithms for billion-parameter models. Source code is available at https://github.com/IST-DASLab/GPTQ-Babai.

cs.LG↗

arXiv2026

Grid Games: The Power of Multiple Grids for Quantizing Large Language Models

A major recent advance in quantization is given by microscaled 4-bit formats such as NVFP4 and MXFP4, quantizing values into small groups sharing a scale, assuming a fixed floating-point grid. In this paper, we study the following natural extension: assume that, for each group of values, we are free to select the "better" among two or more 4-bit grids marked by one or more bits in the scale value. We formalize the power-of-two-grids (PO2) problem, and provide theoretical results showing that practical small-group formats such as MXFP or NVFP can benefit significantly from PO2 grids, while the advantage vanishes for very large groups. On the practical side, we instantiate several grid families, including 1) PO2(NF4), which pairs the standard NF4 normal grid with a learned grid, 2) MPO2, a grid pair that is fully learned over real weights and activations, 3) PO2(Split87), an explicit-zero asymmetric grid and 4) SFP4, a TensorCore-implementable triple which pairs NVFP4 with two shifted variants. Results for post-training quantization of standard open models and pre-training of Llama-like models show that adaptive grids consistently improve accuracy vs single-grid FP4 under both weight-only and weight+activation. Source code is available at https://github.com/IST-DASLab/GridGames.

cs.LG↗

arXiv2026

MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning

With the rise in scale for deep learning models to billions of parameters, the computational cost of fine-tuning remains a significant barrier to deployment. While Low-Rank Adaptation (LoRA) has become the standard for parameter-efficient fine-tuning, the need to set a predefined, static rank $r$ requires exhaustive grid searches to balance efficiency and performance. Existing rank-adaptive solutions such as DyLoRA mitigate this by sampling ranks during the training from a predefined distribution. However, they often yield sub-optimal results at higher ranks due to lack of consistent gradient signals across the full hierarchy of ranks, thus making these methods data-inefficient. In this paper, we propose MatryoshkaLoRA, a general, Matryoshka-inspired training framework for LoRA that learns accurate hierarchical low-rank representations by inserting a fixed, carefully crafted diagonal matrix $P$ between the existing LoRA adapters to scale their sub-ranks accordingly. By introducing this simple modification, our general framework recovers LoRA and DyLoRA only by changing $P$ and ensures all sub-ranks embed the available gradient information efficiently. Our MatryoshkaLoRA supports dynamic rank selection with minimal degradation in accuracy. We further propose Area Under the Rank Accuracy Curve (AURAC), a metric that consistently evaluates the performance of hierarchical low-rank adapters. Our results demonstrate that MatryoshkaLoRA learns more accurate hierarchical low-rank representations than prior rank-adaptive approaches and achieves superior accuracy-performance trade-offs across ranks on the evaluated datasets. Our code is available at https://github.com/IST-DASLab/MatryoshkaLoRA.

cs.CL↗