Related papers: Speculative Decoding: Exploiting Speculative Execu…

Speculative decoding accelerates large language model (LLM) inference by using a smaller draft model to propose tokens, which are then verified by a larger target model. However, selecting an optimal speculation length is critical for…

Recent advances with large language models (LLM) illustrate their diverse capabilities. We propose a novel algorithm, staged speculative decoding, to accelerate LLM inference in small-batch, on-device scenarios. We address the low…

Recent advances in inference-time compute have significantly improved performance on complex tasks by generating long chains of thought (CoTs) using Large Reasoning Models (LRMs). However, this improved accuracy comes at the cost of high…

Inference with Multimodal Large Language Models (MLLMs) is slow due to their large-language-model backbone which suffers from memory bandwidth bottleneck and generates tokens auto-regressively. In this paper, we explore the application of…

Self-speculative decoding is an inference technique for large language models designed to speed up generation without sacrificing output quality. It combines fast, approximate decoding using a compact version of the model as a draft model…

Accelerating the inference of large language models (LLMs) has been a critical challenge in generative AI. Speculative decoding (SD) substantially improves LLM inference efficiency. However, its utility is limited by a fundamental…

Large Language Models (LLMs) increasingly rely on reinforcement learning with verifiable rewards (RLVR) to elicit reliable chain-of-thought reasoning. However, the training process remains bottlenecked by the computationally expensive…

Inference latency stands as a critical bottleneck in the large-scale deployment of Large Language Models (LLMs). Speculative decoding methods have recently shown promise in accelerating inference without compromising the output…

Autoregressive (AR) image models have recently demonstrated remarkable generative capability, but their sequential nature results in significant inference latency. Existing training-free acceleration methods typically verify tokens…

We present Cacheback Decoding, a training-free and model-agnostic speculative decoding method that exploits the locality in language to accelerate Large Language Model (LLM) inference. Cacheback leverages only Least Recently Used (LRU)…

Speculative decoding has demonstrated its effectiveness in accelerating the inference of large language models while maintaining a consistent sampling distribution. However, the conventional approach of training a separate draft model to…

RL post-training of frontier language models is increasingly bottlenecked by autoregressive rollout generation, making rollout acceleration a central systems challenge. Many existing efficiency methods improve throughput by changing the…

Speculative decoding (SD) has been shown to reduce the latency of autoregressive decoding (AD) by 2-3x for small batch sizes. However, increasing throughput and therefore reducing the cost per token requires decoding with large batch sizes.…

Speculative decoding accelerates large language model inference by pairing a target model with a lightweight draft model whose proposed tokens are verified in parallel. A common way to build draft models, like EAGLE3 or DFlash is supervised…

Large language models (LLMs) have shown outstanding performance across numerous real-world tasks. However, the autoregressive nature of these models makes the inference process slow and costly. Speculative decoding has emerged as a…

Speculative decoding accelerates generation by drafting candidates and verifying them in parallel, yet state-of-the-art drafters (e.g., EAGLE) still require N sequential passes to propose N tokens. We present FastEagle, a non-autoregressive…

Performing Retrieval-Augmented Generation (RAG) directly on mobile devices is promising for data privacy and responsiveness but is hindered by the architectural constraints of mobile NPUs. Specifically, current hardware struggles with the…

Cloud-based Large Language Model (LLM) services often face challenges in achieving low inference latency and meeting Service Level Objectives (SLOs) under dynamic request patterns. Speculative decoding, which exploits lightweight models for…

Speculative decoding has been shown as an effective way to accelerate Large Language Model (LLM) inference by using a Small Speculative Model (SSM) to generate candidate tokens in a so-called speculation phase, which are subsequently…

Diffusion Policy (DP) excels in embodied control but suffers from high inference latency and computational cost due to multiple iterative denoising steps. The temporal complexity of embodied tasks demands a dynamic and adaptable computation…