Image de couverture de livre

FairyFuse: Multiplication-Free LLM Inference on CPUs via Fused Ternary Kernels

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zuo, Fei, Xi, Xiaoyan, Zeng, Quanyi, Wang, Feiyu, Leung, Ho Fai
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

RateQuant: Optimal Mixed-Precision KV Cache Quantization via Rate-Distortion Theory
par: Zuo, Fei, et autres
Publié: (2026)

Highly Optimized Kernels and Fine-Grained Codebooks for LLM Inference on Arm CPUs
par: Gope, Dibakar, et autres
Publié: (2024)

AndroidControl-Curated: Revealing the True Potential of GUI Agents through Benchmark Purification
par: Leung, Ho Fai, et autres
Publié: (2025)

Fusing Reward and Dueling Feedback in Stochastic Bandits
par: Wang, Xuchuang, et autres
Publié: (2025)

When Kernels Multiply, Clusters Unify: Fusing Embeddings with the Kronecker Product
par: Wu, Youqi, et autres
Publié: (2025)

Fast and Compact Tsetlin Machine Inference on CPUs Using Instruction-Level Optimization
par: Zeng, Yefan, et autres
Publié: (2025)

Fusing Individualized Treatment Rules Using Secondary Outcomes
par: Gao, Daiqi, et autres
Publié: (2024)

iFairy: the First 2-bit Complex LLM with All Parameters in $\{\pm1, \pm i\}$
par: Wang, Feiyu, et autres
Publié: (2025)

Open-TQ-Metal: Fused Compressed-Domain Attention for Long-Context LLM Inference on Apple Silicon
par: Vegasena, Sai
Publié: (2026)

FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data
par: Feng, Tao, et autres
Publié: (2025)

Fusing Models with Complementary Expertise
par: Wang, Hongyi, et autres
Publié: (2023)

FuseSampleAgg: Fused Neighbor Sampling and Aggregation for Mini-batch GNNs
par: Stanković, Aleksandar
Publié: (2025)

Challenging GPU Dominance: When CPUs Outperform for On-Device LLM Inference
par: Zhang, Haolin, et autres
Publié: (2025)

FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion
par: Han, Xing, et autres
Publié: (2024)

Fuse It or Lose It: Deep Fusion for Multimodal Simulation-Based Inference
par: Schmitt, Marvin, et autres
Publié: (2023)

Scaling DoRA: High-Rank Adaptation via Factored Norms and Fused Kernels
par: Zelenin, Alexandra, et autres
Publié: (2026)

IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs
par: Mao, Yuzhen, et autres
Publié: (2024)

Fused Partial Gromov-Wasserstein for Structured Objects
par: Bai, Yikun, et autres
Publié: (2025)

Low-Cost FlashAttention with Fused Exponential and Multiplication Hardware Operators
par: Alexandridis, Kosmas, et autres
Publié: (2025)

FusedInf: Efficient Swapping of DNN Models for On-Demand Serverless Inference Services on the Edge
par: Taki, Sifat Ut, et autres
Publié: (2024)

An LLM-Tool Compiler for Fused Parallel Function Calling
par: Singh, Simranjit, et autres
Publié: (2024)

Fused Lasso Improves Accuracy of Co-occurrence Network Inference in Grouped Samples
par: Agyapong, Daniel, et autres
Publié: (2025)

Spacing Test for Fused Lasso
par: Tasaka, Rieko, et autres
Publié: (2025)

Fairy2i: Training Complex LLMs from Real LLMs with All Parameters in $\{\pm 1, \pm i\}$
par: Wang, Feiyu, et autres
Publié: (2025)

PAK-UCB Contextual Bandit: An Online Learning Approach to Prompt-Aware Selection of Generative Models and LLMs
par: Hu, Xiaoyan, et autres
Publié: (2024)

A Multi-Armed Bandit Approach to Online Selection and Evaluation of Generative Models
par: Hu, Xiaoyan, et autres
Publié: (2024)

An Information Theoretic Approach to Interaction-Grounded Learning
par: Hu, Xiaoyan, et autres
Publié: (2024)

NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention
par: Zhang, Tianyi, et autres
Publié: (2024)

NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes
par: Sun, Hao-Lun, et autres
Publié: (2023)

Fusing CFD and measurement data using transfer learning
par: Barklage, Alexander, et autres
Publié: (2025)

Learning in Multiple Spaces: Few-Shot Network Attack Detection with Metric-Fused Prototypical Networks
par: Martinez-Lopez, Fernando, et autres
Publié: (2024)

Road Maps as Free Geometric Priors: Weather-Invariant Drone Geo-Localization with GeoFuse
par: Fang, Yunsong, et autres
Publié: (2026)

Hyperspectral Anomaly Detection Fused Unified Nonconvex Tensor Ring Factors Regularization
par: Qin, Wenjin, et autres
Publié: (2025)

THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings
par: Deng, Bowen, et autres
Publié: (2024)

Semantic-Fused Multi-Granularity Cross-City Traffic Prediction
par: Chen, Kehua, et autres
Publié: (2023)

Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesics
par: Zeng, Zhichen, et autres
Publié: (2025)

Improving SMOTE via Fusing Conditional VAE for Data-adaptive Noise Filtering
par: Hong, Sungchul, et autres
Publié: (2024)

Dual-Rerank: Fusing Causality and Utility for Industrial Generative Reranking
par: Zhang, Chao, et autres
Publié: (2026)

Litespark Inference on Consumer CPUs: Custom SIMD Kernels for Ternary Neural Networks
par: Dade, Nii Osae Osae, et autres
Publié: (2026)

A Novel Sliced Fused Gromov-Wasserstein Distance
par: Piening, Moritz, et autres
Publié: (2025)