Imagen de Portada

LAMP: Look-Ahead Mixed-Precision Inference of Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Budzinskiy, Stanislav, Gloser, Marian, Yilmaz, Tolunay, Tham, Ying Hong, Lin, Yuanyi, Fang, Wenyi, Wu, Fan, Petersen, Philipp
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Numerical Analysis
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Numerical Error Analysis of Large Language Models
por: Budzinskiy, Stanislav, et al.
Publicado: (2025)

Matrices over a Hilbert space and their low-rank approximation
por: Budzinskiy, Stanislav
Publicado: (2025)

Entrywise tensor-train approximation of large tensors via random embeddings
por: Budzinskiy, Stanislav
Publicado: (2024)

On the distance to low-rank matrices in the maximum norm
por: Budzinskiy, Stanislav
Publicado: (2023)

Quasioptimal alternating projections and their use in low-rank approximation of matrices and tensors
por: Budzinskiy, Stanislav
Publicado: (2023)

When big data actually are low-rank, or entrywise approximation of certain function-generated matrices
por: Budzinskiy, Stanislav
Publicado: (2024)

Tensor train completion: local recovery guarantees via Riemannian optimization
por: Budzinskiy, Stanislav, et al.
Publicado: (2021)

Low-rank cross approximation of function-valued tensors for reduced-order modeling of parametric PDEs
por: Budzinskiy, Stanislav, et al.
Publicado: (2025)

Optimal error analysis of an interior penalty virtual element method for fourth-order singular perturbation problems
por: Feng, Fang, et al.
Publicado: (2025)

Mixed Precision General Alternating-Direction Implicit Method for Solving Large Sparse Linear Systems
por: Ge, Jifeng, et al.
Publicado: (2025)

Perturbation Analysis for Preconditioned Normal Equations in Mixed Precision
por: Garrison, James E., et al.
Publicado: (2026)

A Mixed Precision Eigensolver Based on the Jacobi Algorithm
por: Zhou, Zhengbo
Publicado: (2025)

Fast Mixed-Precision Real Evaluation
por: Yadrov, Artem, et al.
Publicado: (2025)

Fast Mixed-Precision Real Evaluation
por: Yadrov, Artem, et al.
Publicado: (2024)

Assessing the Performance of Mixed-Precision ILU(0)-Preconditioned Multiple-Precision Real and Complex Krylov Subspace Methods
por: Kouya, Tomonori
Publicado: (2025)

An Adaptive Mixed Precision and Dynamically Scaled Preconditioned Conjugate Gradient Algorithm
por: Guo, Yichen, et al.
Publicado: (2025)

Mixed-Precision in adaptive Runge-Kutta method for large ODE systems
por: Al-Sayed, Mouhamad, et al.
Publicado: (2026)

Guaranteed Approximation Bounds for Mixed-Precision Neural Operators
por: Tu, Renbo, et al.
Publicado: (2023)

Evaluating Numerical Accuracy in Mixed-Precision Computing by Dual-Delta Testing
por: Xie, Peichen
Publicado: (2026)

Pressure-Robust $H(\mathrm{div})$-Conforming HDG Methods for the Steady Stokes Equations with an Application to Tangential Boundary Control
por: Chen, Gang, et al.
Publicado: (2026)

Scalable Bayesian Inference for Nonlinear Conservation Laws
por: Weiland, Tim, et al.
Publicado: (2026)

Variational Bayesian inference for CP tensor completion with side information
por: Budzinskiy, Stanislav, et al.
Publicado: (2022)

Mixed Precision Block-Jacobi Preconditioner: Algorithms, Performance Evaluation and Feature Analysis
por: Tian, Ningxi, et al.
Publicado: (2024)

HPL-MxP Benchmark: Mixed-Precision Algorithms, Iterative Refinement, and Scalable Data Generation
por: Dongarra, Jack, et al.
Publicado: (2025)

Hybrid-Precision Block-Jacobi Preconditioned GMRES Solver for Linear System in Circuit Simulation
por: Zhang, Zijian, et al.
Publicado: (2025)

Optimizing Mixed Quantum Channels via Projected Gradient Dynamics
por: Lin, Matthew M., et al.
Publicado: (2025)

Local and Parallel Mixed‐Precision Finite Element Methods for the Time‐Dependent Incompressible Flows
por: Qingfang Liu, et al.
Publicado: (2025)

A High‐Precision Meshless Method for Time‐Fractional Mixed Diffusion and Wave Equations
por: Zehui Ma, et al.
Publicado: (2025)

Construction of a set of circulant matrix submatrices for faster MDS matrix verification
por: Malakhov, Stanislav S.
Publicado: (2021)

Leveraging Mixed Precision in Exponential Time Integration Methods
por: Balos, Cody J., et al.
Publicado: (2023)

Limited-Precision Stochastic Rounding
por: Arar, El-Mehdi El, et al.
Publicado: (2026)

A Spectral Localization Method for Time-Fractional Integro-Differential Equations with Nonsmooth Data
por: Zhao, Lijing, et al.
Publicado: (2025)

Mixed Finite element method for stress gradient elasticity
por: Lin, Ting, et al.
Publicado: (2025)

Fast Hermitian Diagonalization with Nearly Optimal Precision
por: Shah, Rikhav
Publicado: (2024)

3-Dimensional Adaptive Unstructured Tessellated Look-up Tables for the Approximation of Compton Form Factors
por: Hyde, Charles, et al.
Publicado: (2025)

On Mixed Isogeometric Analysis of Poroelasticity
por: Bekele, Yared W., et al.
Publicado: (2017)

V-ABFT: Variance-Based Adaptive Threshold for Fault-Tolerant Matrix Multiplication in Mixed-Precision Deep Learning
por: Gao, Yiheng, et al.
Publicado: (2026)

Large deviations principles for symplectic discretizations of stochastic linear Schrödinger Equation
por: Chen, Chuchu, et al.
Publicado: (2020)

Mixed Variational Formulation of Coupled Plates
por: Hu, Jun, et al.
Publicado: (2024)

A GPU Accelerated Mixed‐Precision Finite Difference Informed Random Walker ( FDiRW ) Solver for Strongly Inhomogeneous Diffusion Problems
por: Zirui Mao, et al.
Publicado: (2025)