Related papers: Quasar: Quantized Self-Speculative Acceleration fo…

Visual autoregressive (AR) generation models have demonstrated strong potential for image generation, yet their next-token-prediction paradigm introduces considerable inference latency. Although speculative decoding (SD) has been proven…

Low-latency decoding for large language models (LLMs) is crucial for applications like chatbots and code assistants, yet generating long outputs remains slow in single-query settings. Prior work on speculative decoding (which combines a…

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…

The recent advancements in large language models (LLMs) have been extraordinary, yet the escalating inference costs associated with them present challenges in real-world applications. To address these challenges, we propose a novel approach…

The growing gap between the increasing complexity of large language models (LLMs) and the limited computational budgets of edge devices poses a key challenge for efficient on-device inference, despite gradual improvements in hardware…

Large Vision-Language Models (VLMs) have achieved remarkable progress in multimodal understanding, yet they struggle when reasoning over information-intensive images that densely interleave textual annotations with fine-grained graphical…

The synergistic mechanism based on Speculative Decoding (SD) has garnered considerable attention as a simple yet effective approach for accelerating the inference of large language models (LLMs). Nonetheless, the high rejection rates…

Speculative decoding emerges as a pivotal technique for enhancing the inference speed of Large Language Models (LLMs). Despite recent research aiming to improve prediction efficiency, multi-sample speculative decoding has been overlooked…

Speculative decoding is a technique that uses multiple language models to accelerate infer- ence. Previous works have used an experi- mental approach to optimize the throughput of the inference pipeline, which involves LLM training and can…

Speculative decoding accelerates inference for Large Language Models by using a lightweight draft model to propose candidate tokens that are verified in parallel by a larger target model. Prior work shows that the draft model often…

Large language models (LLMs) achieve strong performance across diverse tasks but suffer from high inference latency due to their autoregressive generation. Speculative Decoding (SPD) mitigates this issue by verifying candidate tokens in…

Speculative decoding (SD) accelerates large language model inference by employing a faster draft model for generating multiple tokens, which are then verified in parallel by the larger target model, resulting in the text generated according…

This paper introduces distributed speculative inference (DSI), a novel inference algorithm that is provably faster than speculative inference (SI) [leviathan2023, chen2023, miao2024, sun2025, timor2025] and standard autoregressive inference…

Large Language Models (LLMs) have demonstrated remarkable capabilities in code editing, substantially enhancing software development productivity. However, the inherent complexity of code editing tasks forces existing approaches to rely on…

Speculative decoding (SD) has proven effective for accelerating LLM inference by quickly generating draft tokens and verifying them in parallel. However, SD remains largely unexplored for Large Vision-Language Models (LVLMs), which extend…

Despite extensive efforts to align Large Language Models (LLMs) with human values and safety rules, jailbreak attacks that exploit certain vulnerabilities continuously emerge, highlighting the need to strengthen existing LLMs with…

Speculative sampling has emerged as an important technique for accelerating the auto-regressive generation process of large language models (LLMs) by utilizing a draft-then-verify mechanism to produce multiple tokens per forward pass. While…

Speculative decoding (SPD) accelerates large language model (LLM) inference by letting a smaller draft model propose multiple future tokens that are verified in parallel by a larger target model. The dominant SPD paradigm treats the target…

Scaling the size of language models to tens of billions of parameters has led to impressive performance on a wide range of tasks. At generation, these models are used auto-regressively, requiring a forward pass for each generated token, and…

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…