The paper argues that relying solely on zero‑shot task accuracy is insufficient for evaluating quantized large language models (LLMs) because accuracy ignores changes in the full predictive distribution. It proposes a distribution‑sensitive framework that measures fidelity loss by computing statistical distances—such as Jensen‑Shannon Divergence and Total Variation Distance—between the full‑vocabulary output distributions of a full‑precision BF16 reference and its quantized counterparts. Experiments across five foundation architectures and four reasoning benchmarks show that these divergence metrics increase with stronger quantization, revealing distributional drift that top‑1 accuracy fails to capture, and suggest that mixed‑precision Q4_K schemes can offer lower divergence than uniform Q4_0 at comparable memory usage.
arXiv:2605. 02404v2 Announce Type: replace Abstract: 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.
arXiv:2607. 00908v1 Announce Type: new Abstract: Mixed-precision quantization (MPQ) has become a key technique for deploying large language models under stringent memory and compute constraints.
Squeeze10-LLM is a staged mixed‑precision post‑training quantization framework that reduces 16‑bit LLM weights to an average of 1.6 bits per weight by assigning 80% of weights to 1 bit and 20% to 4 bits. It introduces Post‑Binarization Activation Robustness (PBAR), a weight significance metric that considers activation impact, and Full Information Activation Supervision (FIAS), a strategy that preserves activation information to limit error propagation. Experiments on LLaMA and LLaMA2 demonstrate that Squeeze10‑LLM achieves state‑of‑the‑art performance for sub‑2‑bit weight‑only quantization, raising average accuracy from 43% to 56% on six zero‑shot classification tasks.
arXiv:2607. 08734v1 Announce Type: new Abstract: Post-training quantization is widely used to deploy large language models in resource-constrained settings, yet its evaluation relies almost exclusively on accuracy and perplexity.
InfoQuant is a train‑free method that reshapes activation distributions to be more compatible with low‑bit quantizers. It uses Peak Suppression Orthogonal Transformation (PSOT) and adaptive outlier‑token selection to reduce numerical range while maintaining dispersion, thereby lowering quantization error. Across several large language model families, InfoQuant outperforms existing post‑training quantization and end‑to‑end training baselines, preserving 97% of floating‑point accuracy on average and narrowing the LLaMA‑2 13B performance gap by 42%.
arXiv:2606. 05682v1 Announce Type: cross Abstract: Demand for low-precision inference, including NVFP4-based approaches, has grown as large language models are increasingly deployed in latency and cost constrained production environments.
arXiv:2606. 05682v2 Announce Type: replace Abstract: Demand for low-precision inference, including NVFP4-based approaches, has grown as large language models are increasingly deployed in latency and cost constrained production environments.
The paper demonstrates that layer dropout, also known as stochastic depth, can be effectively used in state‑of‑the‑art large language model (LLM) training. By optimizing the layer distribution, schedule, and optimizer settings, the authors show that layer dropout can reduce training loss while saving up to 25 % of training FLOPs. Additionally, layer dropout enables post‑training optimizations such as early exit and self‑speculative decoding, achieving up to 1.5× inference speedup with negligible accuracy loss across models ranging from 271 M to 8.2 B parameters and datasets up to 160 B tokens.
The paper introduces OnQ, a low‑bit recovery pipeline for quantized large language models that uses on‑policy distillation and candidate‑wise Dynamic KL to address trajectory divergence and distributional misalignment. OnQ starts with block‑wise calibration, then lets the quantized student generate responses and receive full‑precision teacher supervision on its own prefixes, dynamically weighting forward and reverse KL losses per candidate. Experiments on Qwen3 models show that OnQ outperforms baselines on nine benchmarks, especially long‑horizon reasoning, and produces shorter, less truncated responses.
arXiv:2512. 18934v2 Announce Type: replace-cross Abstract: Catastrophic forgetting poses a fundamental challenge in continual learning, particularly when models are quantized for deployment efficiency.
The paper investigates low‑bit quantization for Multimodal Large Language Models (MLLMs), showing that MXFP8 retains near‑lossless performance while 4‑bit formats like MXFP4 and HiF4 cause significant degradation. It identifies activation quantization as the main source of this loss and introduces Residual Fallback Quantization (RFQ), a lightweight framework that adds a quantized residual pathway to improve activation fidelity without architectural changes. Experiments on Wan2.2 and Qwen3‑VL demonstrate that RFQ recovers much of the performance gap to BF16 baselines across generation and reasoning tasks.
The paper introduces CanonQ, a unified quantization‑aware training framework that separates source canonicalization from task‑aware adaptation to enable extreme low‑bit LLM compression. By applying fixed rotations and energy normalization, CanonQ maps heterogeneous tensors to canonical coordinates, allowing frozen Gaussian‑reference codebooks to be reused across layers and models. Joint training then adapts the network to the coupled errors of weight, activation, and KV cache quantization, achieving significant performance gains—up to 14.28× lower perplexity and 57.9% higher zero‑shot accuracy on LLaMA models, and substantial improvements on instruction‑tuned MobileLLM‑Pro‑1B. "whyItMatters":"The framework demonstrates that carefully designed canonicalization and joint training can dramatically improve the efficiency and accuracy of low‑bit quantized large language models, offering a practical path to deploy powerful LLMs with reduced computational and memory footprints."