Cover Image

LoKA: Low-precision Kernel Applications for Recommendation Models At Scale

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Luo, Liang, Ma, Yinbin, Zhu, Quanyu, Kuznetsov, Vasiliy, Chen, Yuxin, Jiao, Jian, Yu, Jiecao, Zhang, Buyun, Tang, Tongyi, Wei, Xiaohan, Zhao, Yanli, Chen, Zeliang, Hao, Yuchen, Ranganathan, Venkatesh, Parab, Sandeep, Yao, Yantao, Naumov, Maxim, Yang, Chunzhi, Li, Shen, Wen, Ellie, Chen, Wenlin, Kolay, Santanu, Tang, Chunqiang
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Wukong: Towards a Scaling Law for Large-Scale Recommendation
by: Zhang, Buyun, et al.
Published: (2024)

Disaggregated Multi-Tower: Topology-aware Modeling Technique for Efficient Large-Scale Recommendation
by: Luo, Liang, et al.
Published: (2024)

Meta Lattice: Model Space Redesign for Cost-Effective Industry-Scale Ads Recommendations
by: Luo, Liang, et al.
Published: (2025)

A sharp upper bound on the third adjacency eigenvalue of a graph
by: Tang, Quanyu
Published: (2026)

Nordhaus--Gaddum type bounds for the complement rank
by: Tang, Quanyu
Published: (2025)

An improved lower bound for Erdős--Szekeres products
by: Tang, Quanyu
Published: (2025)

Schoenberg type inequalities
by: Tang, Quanyu
Published: (2025)

Dual Smale's mean value conjecture for odd polynomials
by: Tang, Quanyu
Published: (2025)

A counterexample to a conjecture of Sárközy on sums and products modulo a prime
by: Tang, Quanyu
Published: (2026)

The Hofstadter consecutive-sum sequence omits infinitely many positive integers
by: Tang, Quanyu
Published: (2026)

Scaling Multi-Node Mixture-of-Experts Inference Using Expert Activation Patterns
by: Bambhaniya, Abhimanyu, et al.
Published: (2026)

Generalizing Lee's conjecture on the sum of absolute values of matrices
by: Tang, Quanyu, et al.
Published: (2025)

Average first-passage times for character sums
by: Tang, Quanyu, et al.
Published: (2025)

Sharp Schoenberg type inequalities and the de Bruin--Sharma problem
by: Tang, Quanyu, et al.
Published: (2025)

Largest Sidon subsets in weak Sidon sets
by: Ma, Jie, et al.
Published: (2026)

An Erdős problem on random subset sums in finite abelian groups
by: Ma, Jie, et al.
Published: (2026)

Proof of a conjectured spectral upper bound on the chromatic number of a graph
by: Tang, Quanyu, et al.
Published: (2025)

Generalizing the Clunie--Hayman construction in an Erdős maximum-term problem
by: He, Yixin, et al.
Published: (2026)

Harmonic LCM patterns and sunflower-free capacity
by: Tang, Quanyu, et al.
Published: (2025)

On a conjecture of Erdős and Graham about the Sylvester's sequence
by: Li, Zheng, et al.
Published: (2025)

On Fuchs's additive intersection problem for the hyperbolic metric
by: He, Yixin, et al.
Published: (2026)

An Erdős--Trotter problem on antichains with multiplicity $r$ on each occurring level
by: He, Yixin, et al.
Published: (2026)

Path-Minimality of $p$-Energy for Connected Graphs
by: Liu, Yinchen, et al.
Published: (2026)

Implicit Turn-Wise Policy Optimization for Proactive User-LLM Interaction
by: Wang, Haoyu, et al.
Published: (2026)

Cyclic Group Projection for Enumerating Quasi-Cyclic Codes Trapping Sets
by: Usatyuk, Vasiliy, et al.
Published: (2024)

Number of independent transversals in multipartite graphs
by: Tang, Yantao, et al.
Published: (2025)

The smallest denominator not contained in a unit fraction decomposition of $1$ with fixed length
by: van Doorn, Wouter, et al.
Published: (2025)

A low‐profile four‐degrees of freedom antenna by collocating a ±45°‐polarized dipole and a dual‐polarized microstrip antenna with broadside radiations
by: Buyun Wang, et al.
Published: (2024)

SOLARIS: Speculative Offloading of Latent-bAsed Representation for Inference Scaling
by: Liu, Zikun, et al.
Published: (2026)

Counterfactual Self-Questioning for Stable Policy Optimization in Language Models
by: Parab, Mandar
Published: (2025)

Fig. 1 in Descriptive morphometric analysis of three common bivalve species from Chandipur, Odisha, Eastern India
by: Kolay, S K
Published: (2024)

Fig. 3 in Descriptive morphometric analysis of three common bivalve species from Chandipur, Odisha, Eastern India
by: Kolay, S K
Published: (2024)

The separable case of Kadison's problem on orthonormal bases of unitaries for type $\mathrm{II}_1$ factors
by: He, Yixin, et al.
Published: (2026)

On the Positive and Negative $p$-Energies of Graphs under Edge Addition
by: Tang, Quanyu, et al.
Published: (2024)

Factorization of invariant polynomials and generalized spectral characterizations of graphs
by: Wang, Wei, et al.
Published: (2026)

Optimal universal growth for integral means of normalized logarithmic derivatives in the Carathéodory class
by: He, Yixin, et al.
Published: (2026)

A Solution to a Problem of Rubel on Two-Parameter Normal Families of Entire Functions
by: He, Yixin, et al.
Published: (2026)

A Spectral Lower Bound on Chromatic Numbers using $p$-Energy
by: Elphick, Clive, et al.
Published: (2025)

Inertia, Independence and Expanders
by: Tang, Quanyu, et al.
Published: (2025)

The Generation of All Regular Rational Orthogonal Matrices
by: Tang, Quanyu, et al.
Published: (2024)