Imagen de Portada

READER: Retrieval-Assisted Drafter for Efficient LLM Inference

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Divilkovskiy, Maxim, Malygin, Vitaly, Zlobin, Sergey, Ilyushin, Stanislav, Isali, Sultan, Kalugin, Vasily, Aitassova, Nuriza, Yi, Fei, Zeng, Weidi
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Stochastic Decentralized Optimization of Non-Smooth Convex and Convex-Concave Problems over Time-Varying Networks
por: Divilkovskiy, Maxim, et al.
Publicado: (2025)

Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters
por: Yi, Euiin, et al.
Publicado: (2024)

Uncertainty-Aware Evaluation for Vision-Language Models
por: Kostumov, Vasily, et al.
Publicado: (2024)

An Extensible Julia Toolkit for Symmetry-Aware Dual Space Phasing in Arbitrary Dimensions
por: Kalugin, Pavel
Publicado: (2025)

ParallelSpec: Parallel Drafter for Efficient Speculative Decoding
por: Xiao, Zilin, et al.
Publicado: (2024)

Mamba Drafters for Speculative Decoding
por: Choi, Daewon, et al.
Publicado: (2025)

LexDrafter: Terminology Drafting for Legislative Documents using Retrieval Augmented Generation
por: Chouhan, Ashish, et al.
Publicado: (2024)

Conceptual Design of A 20 T Dipole Based on Hybrid REBCO/Nb3Sn Cos-theta Coil*
por: Zlobin, A. V.
Publicado: (2024)

THE RELATIONSHIP BETWEEN STYLE AND READER ENGAGEMENT
por: Ma'ripov Jalolxon Kamoliddin o'g'li, et al.
Publicado: (2025)

Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter
por: Hu, Qinghao, et al.
Publicado: (2025)

Recurrent Drafter for Fast Speculative Decoding in Large Language Models
por: Cheng, Yunfei, et al.
Publicado: (2024)

DrafterBench: Benchmarking Large Language Models for Tasks Automation in Civil Engineering
por: Li, Yinsheng, et al.
Publicado: (2025)

SD$^2$: Self-Distilled Sparse Drafters
por: Lasby, Mike, et al.
Publicado: (2025)

Steering Pretrained Drafters during Speculative Decoding
por: Berdoz, Frédéric, et al.
Publicado: (2025)

Multi-Drafter Speculative Decoding with Alignment Feedback
por: Kim, Taehyeon, et al.
Publicado: (2026)

Pipeline for Verifying LLM-Generated Mathematical Solutions
por: Sazonova, Varvara, et al.
Publicado: (2026)

On Irreducibility of Tensor Products of Yangian Modules
por: Nazarov, Maxim, et al.
Publicado: (1997)

SOCIAL AND PHILOSOPHICAL ESSENCE OF THE PROBLEM OF SATISFACTION OF READER CONSUMPTION
por: PARVİZ FİRUDİNOGLU KAZİMİ, et al.
Publicado: (2025)

Coupling without Communication and Drafter-Invariant Speculative Decoding
por: Daliri, Majid, et al.
Publicado: (2024)

Optimization of Retrieval-Augmented Generation Context with Outlier Detection
por: Bulgakov, Vitaly
Publicado: (2024)

Notes on peculiarities of Schwinger--DeWitt technique: one-loop double poles, total-derivative terms and determinant anomalies
por: Barvinsky, Andrei O., et al.
Publicado: (2024)

In the Search of Optimal Tree Networks: Hardness and Heuristics
por: Buzdalov, Maxim, et al.
Publicado: (2024)

READING AS AN INTERACTION BETWEEN THE READER AND THE TEXT: CONCEPTIONS AND PRACTICES IN THE PNAIC NOTEBOOKS
por: Nörnberg, Marta, et al.
Publicado: (2021)

THE ALGORITHMIC READER: UNCOVERING AI'S CONTEXTUAL BLIND SPOTS IN POETRY INTERPRETATION
por: Desthia Amalia, SS, M. Sas
Publicado: (2026)

SafeAgent: A Runtime Protection Architecture for Agentic Systems
por: Liu, Hailin, et al.
Publicado: (2026)

SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM Inference
por: Zhao, Yi, et al.
Publicado: (2025)

Dynamic interchange between two protonation states is characteristic of active sites of cholinesterases
por: Alexander Zlobin, et al.
Publicado: (2024)

Not-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMs
por: Liu, Hongyi, et al.
Publicado: (2025)

Reseña de "THE YOUNG LORDS: A READER" de Darrel Enck-Wanzer
por: Saulo Colón Zavala
Publicado: (2011)

A SURVEY OF MICROFICHE READERS AND READER-PRINTERS CURRENTLY MANUFACTURED IN THE UNITED STATES.
por: TATE, VERNON D., et al.
Publicado: (1967)

FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference
por: Liu, Guangda, et al.
Publicado: (2025)

Star Attention: Efficient LLM Inference over Long Sequences
por: Acharya, Shantanu, et al.
Publicado: (2024)

SpecDiff-2: Scaling Diffusion Drafter Alignment For Faster Speculative Decoding
por: Sandler, Jameson, et al.
Publicado: (2025)

Crust Macrofracturing as the Evidence of the Last Deglaciation
por: Aleshin, Igor, et al.
Publicado: (2022)

Ribosomal Proteins as Exosomal Cargo: Random Passengers or Crucial Players in Carcinogenesis?
por: Dmitri Graifer, et al.
Publicado: (2025)

Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval
por: Vazhentsev, Artem, et al.
Publicado: (2026)

DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
por: Xiao, Guangxuan, et al.
Publicado: (2024)

A Sanity Check on Composed Image Retrieval
por: Liu, Yikun, et al.
Publicado: (2026)

OmniDraft: A Cross-vocabulary, Online Adaptive Drafter for On-device Speculative Decoding
por: Ramakrishnan, Ramchalam Kinattinkara, et al.
Publicado: (2025)

CORAL: Learning Consistent Representations across Multi-step Training with Lighter Speculative Drafter
por: Weng, Yepeng, et al.
Publicado: (2025)