RESEARCH
NLP
Efficient Speculative Decoding for Llama at Scale: Challenges and Solutions
August 12, 2025
Abstract
Speculative decoding is a standard method for accelerating the inference speed of large language models. However, scaling it for production environments poses several engineering challenges, including efficiently implementing different operations (e.g., tree attention and multi-round speculative decoding) on GPU. In this paper, we detail the training and inference optimization techniques that we have implemented to enable EAGLE-based speculative decoding at a production scale for Llama models. With these changes, we achieve a new state-of-the-art inference latency for Llama models. For example, Llama4 Maverick decodes at a speed of about 4 ms per token (with a batch size of one) on 8 NVIDIA H100 GPUs, which is 10% faster than the previously best known method. Furthermore, for EAGLE-based speculative decoding, our optimizations enable us to achieve a speed-up for large batch sizes between 1.4x and 2.0x at production scale.
AUTHORS
Written by
GenAI and Infra Teams
Publisher
arXiv
Related Publications
May 12, 2026
HUMAN & MACHINE INTELLIGENCE
RESEARCH
NeuralSet: A High-Performing Python Package for Neuro-AI
Corentin Bel, Linnea Evanson, Julien Gadonneix, Andrea Santos Revilla, Mingfang (Lucy) Zhang, Julie Bonnaire, Charlotte Caucheteux, Alexandre Défossez, Théo Desbordes, Pablo Diego-Simón, Shubh Khanna, Juliette Millet, Pierre Orhan, Saarang Panchavati, Antoine Ratouchniak, Alexis Thual, Hubert Jacob Banville, Jarod Levy, Jean Remi King, Josephine Raugel, Jérémy Rapin, Katelyn Begany, Marlene Careil, Simon Dahan, Sophia Houhamdi, Stéphane d'Ascoli, Teon Brooks, Yohann Benchetrit
May 12, 2026
May 06, 2026
HUMAN & MACHINE INTELLIGENCE
RESEARCH
NeuralBench: A Unifying Framework to Benchmark NeuroAI Models
Saarang Panchavati, Antoine Ratouchniak, Mingfang (Lucy) Zhang, Elisa Cascardi, Hubert Banville, Jarod Levy, Jean-Rémi King, Jérémy Rapin, Katelyn Begany, Marlene Careil, Simon Dahan, Stéphane d'Ascoli, Teon Brooks, Yohann Benchetrit
May 06, 2026
May 04, 2026
NLP
Compute Optimal Tokenization
Sachin Mehta, Alisa Liu, Margaret Li, Artidoro Pagnoni, Gargi Ghosh, Luke Zettlemoyer, Mike Lewis, Srini Iyer, Tomasz Limisiewicz
May 04, 2026
April 16, 2026
RESEARCH
AIRA₂: Overcoming Bottlenecks in AI Research Agents
Nicola Cancedda, Pontus Stenetorp, Alexis Audran-Reiss, Alisia Lupidi, Anton Protopopov, Bassel Al Omari, Carole-Jean Wu, Derek Dunfield, Despoina Magka, Edan Toledo, Hela Momand, Ishita Mediratta, Jakob Foerster, Jean-Christophe Gagnon-Audet, Karen Hambardzumyan, Kelvin Niu, Martin Josifoski, Michael Kuchnik, Michael Shvartsman, Nicolas Baldwin, Parth Pathak, Rishi Hazra, Tatiana Shavrina, Thomas Simon Foster, Yoram Bachrach
April 16, 2026
Help Us Pioneer The Future of AI
We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.
Our approach
Latest news
Foundational models
Meta © 2026