Related papers: Tandem Transformers for Inference Efficient LLMs
The rapid development of large language model (LLM)-based agents has unlocked new possibilities for autonomous multi-turn reasoning and tool-augmented decision-making. However, their real-world deployment is hindered by severe…
Generative Large Language Models (LLMs) have achieved remarkable advancements in various NLP tasks. However, these advances have not been reflected in the translation task, especially those with moderate model sizes (i.e., 7B or 13B…
Reasoning-oriented Large Language Models (LLMs) often rely on generating explicit tokens step by step, and their effectiveness typically hinges on large-scale supervised fine-tuning or reinforcement learning. While Chain-of-Thought (CoT)…
Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generating multiple tokens using a single target forward pass.…
Adjusting the latency, power, and accuracy of natural language understanding models is a desirable objective of an efficient architecture. This paper proposes an efficient Transformer architecture that adjusts the inference computational…
Large language models (LLMs) have rapidly progressed into general-purpose agents capable of solving a broad spectrum of tasks. However, current models remain inefficient at reasoning: they apply fixed inference-time compute regardless of…
The remarkable success of Chain-of-Thought (CoT), which enhances performance by scaling generation steps at test-time, inspires us to ask: can we leverage a similar scaling of computational steps during pretraining to improve the generation…
Speculative decoding has emerged as a promising technique to accelerate the inference of Large Language Models (LLMs) by employing a small language model to draft a hypothesis sequence, which is then validated by the LLM. The effectiveness…
We present speculative sampling, an algorithm for accelerating transformer decoding by enabling the generation of multiple tokens from each transformer call. Our algorithm relies on the observation that the latency of parallel scoring of…
The transition from standard generative AI to \emph{reasoning-centric architectures}, exemplified by models capable of extensive Chain-of-Thought~(CoT) processing, marks a fundamental paradigm shift in system requirements. Unlike…
Transformer based language models (LMs) demonstrate increasing performance with scale across a wide variety of tasks. Scale alone however cannot enable models to solve tasks that require access to ephemeral, changing, or private data that…
The growing demand for on-device large language model (LLM) inference highlights the need for efficient mobile edge computing (MEC) solutions, especially in resource-constrained settings. Speculative decoding offers a promising solution by…
Powerful foundation models, including large language models (LLMs), with Transformer architectures have ushered in a new era of Generative AI across various industries. Industry and research community have witnessed a large number of new…
Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More…
Autoregressive (AR) generation is the standard decoding paradigm for Large Language Models (LLMs), but its token-by-token nature limits parallelism at inference time. Diffusion Language Models (DLLMs) offer parallel decoding by recovering…
As large language models (LLMs) have shown great success in many tasks, they are used in various applications. While a lot of works have focused on the efficiency of single-LLM application (e.g., offloading, request scheduling, parallelism…
Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs for text generation, with the potential to decode multiple tokens in a single iteration. However, none of the existing open-source…
Large language models (LLMs) have achieved near-human performance across diverse reasoning tasks, yet their deployment on resource-constrained Internet-of-Things (IoT) devices remains impractical due to massive parameter footprints and…
We present a novel inference scheme, self-speculative decoding, for accelerating Large Language Models (LLMs) without the need for an auxiliary model. This approach is characterized by a two-stage process: drafting and verification. The…
Diffusion Large Language Models (DLLMs) offer a compelling alternative to Auto-Regressive models, but their deployment is constrained by high decoding cost. In this work, we identify a key inefficiency in DLLM decoding: while computation is…