Image de couverture de livre

On multi-token prediction for efficient LLM inference

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Mehra, Somesh, Garcia, Javier Alonso, Mauch, Lukas
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

The pitfalls of next-token prediction
par: Bachmann, Gregor, et autres
Publié: (2024)

Language models are better than humans at next-token prediction
par: Shlegeris, Buck, et autres
Publié: (2022)

Where is the signal in tokenization space?
par: Geh, Renato Lui, et autres
Publié: (2024)

GaLLoP: Gradient-based Sparse Learning on Low-Magnitude Parameters
par: Choudhary, Anand, et autres
Publié: (2025)

QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference
par: Kim, Taesu, et autres
Publié: (2024)

Visualizing token importance for black-box language models
par: Rauba, Paulius, et autres
Publié: (2025)

Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs
par: Singh, Aaditya K., et autres
Publié: (2024)

Do language models plan ahead for future tokens?
par: Wu, Wilson, et autres
Publié: (2024)

Is Sanskrit the most token-efficient language? A quantitative study using GPT, Gemini, and SentencePiece
par: Kumar, Anshul
Publié: (2026)

Statistical multi-metric evaluation and visualization of LLM system predictive performance
par: Ackerman, Samuel, et autres
Publié: (2025)

Looking beyond the next token
par: Thankaraj, Abitha, et autres
Publié: (2025)

Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction
par: Nagarajan, Vaishnavh, et autres
Publié: (2025)

Byte-token Enhanced Language Models for Temporal Point Processes Analysis
par: Kong, Quyu, et autres
Publié: (2025)

Shaping capabilities with token-level data filtering
par: Rathi, Neil, et autres
Publié: (2026)

Implicit Geometry of Next-token Prediction: From Language Sparsity Patterns to Model Representations
par: Zhao, Yize, et autres
Publié: (2024)

Sample-efficient LLM Optimization with Reset Replay
par: Liu, Zichuan, et autres
Publié: (2025)

Scaling Transformer to 1M tokens and beyond with RMT
par: Bulatov, Aydar, et autres
Publié: (2023)

AtteSTNet -- An attention and subword tokenization based approach for code-switched text hate speech detection
par: Shingi, Geet, et autres
Publié: (2021)

Interpretable Next-token Prediction via the Generalized Induction Head
par: Kim, Eunji, et autres
Publié: (2024)

COMPACT: Common-token Optimized Model Pruning Across Channels and Tokens
par: Kwek, Eugene, et autres
Publié: (2025)

AtP*: An efficient and scalable method for localizing LLM behaviour to components
par: Kramár, János, et autres
Publié: (2024)

Assessing LLM Text Detection in Educational Contexts: Does Human Contribution Affect Detection?
par: Gehring, Lukas, et autres
Publié: (2025)

Exploring space efficiency in a tree-based linear model for extreme multi-label classification
par: Lin, He-Zhe, et autres
Publié: (2024)

PreFT: Prefill-only finetuning for efficient inference
par: Lanpouthakoun, Andrew, et autres
Publié: (2026)

Essential-Web v1.0: 24T tokens of organized web data
par: AI, Essential, et autres
Publié: (2025)

All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling
par: Marconato, Emanuele, et autres
Publié: (2024)

You only need 4 extra tokens: Synergistic Test-time Adaptation for LLMs
par: Xu, Yijie, et autres
Publié: (2025)

Global-Order GFlowNets
par: Pastor-Pérez, Lluís, et autres
Publié: (2025)

LLM-based feature generation from text for interpretable machine learning
par: Balek, Vojtěch, et autres
Publié: (2024)

Are LLM-based methods good enough for detecting unfair terms of service?
par: Frasheri, Mirgita, et autres
Publié: (2024)

Transformers for molecular property prediction: Domain adaptation efficiently improves performance
par: Sultan, Afnan, et autres
Publié: (2025)

Amortizing intractable inference in large language models
par: Hu, Edward J., et autres
Publié: (2023)

OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inference
par: Shin, Seungjun, et autres
Publié: (2025)

Entropy trajectory shape predicts LLM reasoning reliability: A diagnostic study of uncertainty dynamics in chain-of-thought
par: Zhao, Xinghao
Publié: (2026)

Publicly-Detectable Watermarking for Language Models
par: Fairoze, Jaiden, et autres
Publié: (2023)

POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation
par: Qiu, Zeju, et autres
Publié: (2026)

Kanana: Compute-efficient Bilingual Language Models
par: Kanana LLM Team, et autres
Publié: (2025)

Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning
par: Tan, Qitao, et autres
Publié: (2025)

LLM Unlearning with LLM Beliefs
par: Li, Kemou, et autres
Publié: (2025)

NorMuon: Making Muon more efficient and scalable
par: Li, Zichong, et autres
Publié: (2025)