Mixed-Precision Quantization

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

15 new papers

A weekly snapshot of new work published in Mixed-Precision Quantization.

Period ending 2026-09-14

13 new papers

A weekly snapshot of new work published in Mixed-Precision Quantization.

Period ending 2026-09-07

12 new papers

A weekly snapshot of new work published in Mixed-Precision Quantization.

Inside this field

Focused directions

Focused topic

Quantization

Within Mixed-Precision Quantization

172 papersExplore

Focused topic

Large Language Model Quantization

Within Mixed-Precision Quantization

134 papersExplore

Focused topic

Weight-Only Quantization

Within Mixed-Precision Quantization

69 papersExplore

Focused topic

Quantizer

Within Mixed-Precision Quantization

54 papersExplore

Focused topic

Mixed-Precision Quantization

Within Mixed-Precision Quantization

51 papersExplore

Focused topic

Full-Precision Performance

Within Mixed-Precision Quantization

36 papersExplore

Focused topic

Floating-Point

Within Mixed-Precision Quantization

25 papersExplore

Focused topic

Systematic Fp16 Divergence

Within Mixed-Precision Quantization

25 papersExplore

Focused topic

Extreme Low-Bit Quantization

Within Mixed-Precision Quantization

22 papersExplore

Focused topic

W4A4 Quantization

Within Mixed-Precision Quantization

22 papersExplore

Focused topic

Fp8

Within Mixed-Precision Quantization

20 papersExplore

Focused topic

Low-Bit

Within Mixed-Precision Quantization

19 papersExplore

464 papers

Latest in Mixed-Precision Quantization

Browse all topics →

Fast and Stable Triangular Inversion for Delta-Rule Linear Transformers
May 20, 2026Aleksandros Sobczyk, Gioele Gottardo, Christos K. Matzoros +4Quadratic Attention Full-Precision Performance
RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
May 20, 2026Siyong Jian, Siyuan Li, Luyuan Zhang +5Text-To-Image Large Language Model Quantization
FTerViT: Fully Ternary Vision Transformer
May 20, 2026Szymon Ruciński, Pietro Bonazzi, Engin Türetken +3Self-Supervised Vision Transformers Vision Transformer
Q-ARVD: Quantizing Autoregressive Video Diffusion Models
May 20, 2026Siao Tang, Xinyin Ma, Gongfan Fang +2Autoregressive Video Diffusion Quantizer
Runtime-Certified Bounded-Error Quantized Attention
May 20, 2026Dean CalverKey-Value Cache Quantization Systematic Fp16 Divergence
Instant GPU Efficiency Visibility at Fleet Scale
May 20, 2026Connor Pedersen, Dong H. Ahn, Michel Migdal +2Single Graphics Processing Unit High-Performance Computing
MGVQ: Synergizing Multi-dimensional Sensitivity-Aware and Gradient-Hessian Fusion for Vector Quantization
May 20, 2026Zhong Wang, Zukang Xu, Xing Hu +1Large Language Model Quantization Quantization
ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
May 19, 2026Arash Akbari, Arman Akbari, Masih Eskandar +11Weight-Only Quantization Vision-Language-Action Models
Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor
May 19, 2026Xiaocan Li, Shiliang Wu, Zheng ShenW4A4 Quantization Truncation
Block-Sphere Vector Quantization
May 19, 2026Heesang Ann, Joongkyu Lee, Min-hwan OhCalibration-Free Low-Bit Vector Quantization Extreme Low-Bit Quantization
Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models
May 19, 2026Yi Zhong, Haotong Qin, Xindong Zhang +2Quantization Cross-Modal Learning
AR1-ZO: Topology-Aware Rank-1 Zeroth-Order Queries for High-Rank LoRA Fine-Tuning
May 19, 2026Ziye Chen, Hongbin Lin, Chenyu Zhang +3Low-Rank Adaptation Zeroth-Order Optimization
OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond
May 19, 2026Zunhai Su, Rui Yang, Chao Zhang +11Key-Value Cache Quantization Key-Value Cache Compression
Quant.npu: Enabling Efficient Mobile NPU Inference for on-device LLMs via Fully Static Quantization
May 19, 2026Jinghe Zhang, Daliang Xu, Chenghua Wang +5Weight-Only Quantization Neural Processing Units
K-Quantization and its Impact on Output Performance
May 19, 2026Robin Baki Davidsson, Pierre NuguesLarge Language Model Quantization Mmlu-Pro
TORQ: Two-Level Orthogonal Rotation for MXFP4 Quantization
May 19, 2026Zukang Xu, Xing Hu, Dawei YangW4A4 Quantization Quantization
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
May 18, 2026Yukang Chen, Luozhou Wang, Wei Huang +13Long Video Generation Consumer Graphics Processing Units
GAMMA: Global Bit Allocation for Mixed-Precision Models under Arbitrary Budgets
May 18, 2026Zhangyang Yao, Haiyan Zhao, Haoyu Wang +3Mixed-Precision Quantization Token Budgets
Token-Space Mask Prediction for Efficient Vision Transformer Segmentation
May 18, 2026Calvin Galagain, Martyna Poreba, François GouletteSelf-Supervised Vision Transformers Convolutional Neural Networks
MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization
May 18, 2026Le Su, Xing Luo, Zhi JinWeight-Only Quantization Low-Bit
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
May 18, 2026Zhongzhu Zhou, Donglin Zhuang, Jisen Li +4Key-Value Cache Quantization Quantization
Covariance Structure and Coordinate Heterogeneity Govern Binary Quantization of Contrastive Embeddings
May 17, 2026Wenxuan XiaoQuantizer Embedding Dimension
TriAxialKV: Toward Extreme Low-Precision KV-Cache Quantization for Agentic Inference Tasks
May 16, 2026Hanzhang Shen, Haoran Wu, Yiren Zhao +1Key-Value Cache Quantization LLM Inference Efficiency
When Bits Break Recourse: Counterfactual-Faithful Quantization
May 16, 2026Chaymae Yahyati, Ismail Lamaakal, Khalid El Makkaoui +1Quantization Distributional Fidelity
CAR-SAM: Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything Model
May 16, 2026Houji Wen, Jiangyong Yu, Jun Li +1Weight-Only Quantization Quantization
E-PMQ: Expert-Guided Post-Merge Quantization with Merged-Weight Anchoring
May 16, 2026Wenjun Wang, Yanggan Gu, Shuo Cai +4Weight-Only Quantization Quantization
DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers
May 16, 2026Sayeh Sharify, Mahsa Salmani, Hesham MostafaMultimodal Diffusion Transformers Low-Bit
Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer
May 15, 2026Yipu Zhang, Jintao Cheng, Weilun Feng +5Feed-Forward 3D Reconstruction Quantization
Measuring Maximum Activations in Open Large Language Models
May 15, 2026Luxuan Chen, Han Tian, Xinran Chen +9Large Language Model Quantization Model Activations
Widening the Gap: Exploiting LLM Quantization via Outlier Injection
May 14, 2026Xiaohua Zhan, Kazuki Egashira, Robin Staab +2Large Language Model Quantization Quantization
Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution
May 14, 2026Saisab Sadhu, Pratinav Seth, Vinay Kumar SankarapuQuantization Forgetting
Nonlinear Bipolar Compensation: Handling Outliers in Post-Training Quantization
May 14, 2026Peilin Sun, Jianxin WuWeight-Only Quantization Outliers
XFP: Quality-Targeted Adaptive Codebook Quantization with Sparse Outlier Separation for LLM Inference
May 14, 2026Thomas WittExtreme Low-Bit Quantization LLM Inference Efficiency
Exploring Bottlenecks in VLM-LLM Navigation: How 3D Scene Understanding Capability Impacts Zero-Shot VLN
May 14, 2026Ziyi Xia, Chaoran Xiong, Litao Wei +2Vision-Language Navigation 3D Scene Understanding
Asymmetric Generative Recommendation via Multi-Expert Projection and Multi-Faceted Hierarchical Quantization
May 14, 2026Bin Huang, Xin Wang, Junwei Pan +6Large-Scale Recommendation Systems Recommendation
RQ-MoE: Residual Quantization via Mixture of Experts for Efficient Input-Dependent Vector Compression
May 14, 2026Zhengjia Zhong, Shuyan Ke, Zaizhou Lin +3Calibration-Free Low-Bit Vector Quantization Codebooks
Provable Quantization with Randomized Hadamard Transform
May 13, 2026Ying Feng, Piotr Indyk, Michael Kapralov +2Calibration-Free Low-Bit Vector Quantization Quantization
High-Rate Quantized Matrix Multiplication II
May 13, 2026Or Ordentlich, Yury PolyanskiyWeight-Only Quantization Matrix Multiplication
ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin
May 13, 2026Jaeyung Kim, YoungJoon YooCalibration-Free Low-Bit Vector Quantization Variational Autoencoder
Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference
May 13, 2026Lingchao Zheng, Yuwei Fan, Jun Li +5Quantizer Systematic Fp16 Divergence
Search Your Block Floating Point Scales!
May 12, 2026Tanmaey Gupta, Hayden Prairie, Xiaoxia Wu +10Quantization Floating-Point
Output Composability of QLoRA PEFT Modules for Plug-and-Play Attribute-Controlled Text Generation
May 12, 2026Michela Lorandi, Anya BelzParameter-Efficient Fine-Tuning Large Language Model Quantization
Grid Games: The Power of Multiple Grids for Quantizing Large Language Models
May 12, 2026Vage Egiazarian, Erik Schultheis, Andrei Panferov +3Large Language Model Quantization Quantization
SOAR: Scale Optimization for Accurate Reconstruction in NVFP4 Quantization
May 12, 2026Chengzhu Bao, Xianglong Yan, Zhiteng Li +3Quantization
MuonQ: Enhancing Low-Bit Muon Quantization via Directional Fidelity Optimization
May 12, 2026Yupeng Su, Ruijie Zhang, Ziyue Liu +2Muon Optimizer Quantization
ADMM-Q: An Improved Hessian-based Weight Quantizer for Post-Training Quantization of Large Language Models
May 11, 2026Ryan Lucas, Mehdi Makni, Xiang Meng +2Quantization Model Weights
DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices
May 11, 2026Chenyang Song, Weilin Zhao, Xu Han +3Mixture-Of-Expert Inference Mixture-of-Experts Models
LoKA: Low-precision Kernel Applications for Recommendation Models At Scale
May 11, 2026Liang Luo, Yinbin Ma, Quanyu Zhu +21Fp8 Recommendation
ConQuR: Corner Aligned Activation Quantization via Optimized Rotations for LLMs
May 11, 2026Chayne Thrash, Ali Abbasi, Soheil KolouriLarge Language Model Quantization Model Activations
BCJR-QAT: A Differentiable Relaxation of Trellis-Coded Weight Quantization
May 11, 2026Venugopalan IyengarQuantization Large Language Model Decoder
Theory-optimal Quantization Based on Flatness
May 11, 2026Xiusheng Huang, Zhe Li, Xuanwu Yin +5Large Language Model Quantization Quantization
Pretraining large language models with MXFP4 on Native FP4 Hardware
May 11, 2026Musa Cim, Poovaiah Palangappa, Miro Hodak +3W4A4 Quantization Fp8
PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models
May 10, 2026Yongsen Cheng, Kai Liu, Kaiwen Tao +5Weight-Only Quantization Permutation
TileQ: Efficient Low-Rank Quantization of Mixture-of-Experts with 2D Tiling
May 10, 2026Hongyaoxing Gu, Xinzhe Chen, Lijuan Hu +1Mixture-Of-Expert Inference Mixed-Precision Quantization
Fitting Is Not Enough: Smoothness in Extremely Quantized LLMs
May 9, 2026Yuzhuang Xu, Xu Han, Yuxuan Li +2Large Language Model Quantization Smoothing
LAQuant: A Simple Overhead-free Large Reasoning Model Quantization by Layer-wise Lookahead Loss
May 9, 2026Euntae Choi, Sumin Song, Sungjoo YooLarge Language Model Quantization Extreme Low-Bit Quantization
AAAC: Activation-Aware Adaptive Codebooks for 4-bit LLM Weight Quantization
May 9, 2026Beshr IslamBouli, David JinLarge Language Model Quantization Weight-Only Quantization
RDKV: Rate-Distortion Bit Allocation for Joint Eviction and Quantization of the KV Cache
May 8, 2026Junkai Zhang, Hang Guo, Luca Benini +1Key-Value Cache Compression Key-Value Cache
CktFormalizer: Autoformalization of Natural Language into Circuit Representations
May 8, 2026Jing Xiong, Qi Han, Chenchen Ding +4Hardware Description Languages Vhdl
Direction-Preserving Number Representations
May 8, 2026Bardia Zadeh, George A. ConstantinidesFull-Precision Performance Calibration-Free Low-Bit Vector Quantization

May 20, 2026 · cs.LGJ/K move · Enter open · S save

Fast and Stable Triangular Inversion for Delta-Rule Linear Transformers

Aleksandros Sobczyk, Gioele Gottardo, Christos K. Matzoros, Mirko De Vita+3

Computing Systems Lab Huawei Technologies2026 Switzerland

Linear attention has emerged as a cornerstone for efficient long-context architectures, as evidenced by its integration into state-of-the-art open-source models including Qwen3.5/3.6, Kimi Linear, and RWKV-7. Models that incorporate linear attention layers with the so-called Delta-Rule involve the inversion of triangular matrices as a core sub-routine. This operation often forms a performance bottleneck, and, due to its high-sensitivity to numerical errors, it can significantly deteriorate end-to-end model accuracy if it is not carefully implemented. This work provides a systematic analysis of both direct and iterative triangular inversion algorithms, targeting methods that are rich in matrix products, and, therefore, have the potential to efficiently utilize modern hardware. To that end, our analysis covers a broad spectrum of mathematical and practical aspects, with a heavy focus on numerical stability, computational complexity, and, ultimately, hardware efficiency and practical considerations. We provide a rigorous experimental evaluation to verify these properties in practical scenarios, and in low-precision floating-point representations, highlighting the strengths and limitations of each method. Performance benchmarks on NPUs reveal up to

4.3\times

speed-up against the state-of-the-art implementations of SGLang for triangular matrix inversion, leading to significant performance improvements on the entire layer level, while maintaining full end-to-end model accuracy.

Quadratic Attention Full-Precision Performance Efficient Long-Context Inference

Open paper Ask about it PDF