Related papers: DART: Diffusion-Inspired Speculative Decoding for …

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…

Small language models (SLMs) support efficient deployments on resource-constrained edge devices, but their limited capacity compromises inference performance. Retrieval-augmented generation (RAG) is a promising solution to enhance model…

Speculative decoding is a widely used method that accelerates the generation process of large language models (LLMs) with no compromise in model performance. It achieves this goal by using an existing smaller model for drafting and then…

This paper introduces Multimodal Speculative Decoding (MSD) to accelerate Multimodal Large Language Models (MLLMs) inference. Speculative decoding has been shown to accelerate Large Language Models (LLMs) without sacrificing accuracy.…

Recent unified multimodal large language models (MLLMs) have shown impressive capabilities, incorporating chain-of-thought (CoT) reasoning for enhanced text-to-image generation. However, existing approaches remain limited, either treating…

Autoregressive (AR) large language models (LLMs) have achieved remarkable performance across a wide range of natural language tasks, yet their inherent sequential decoding limits inference efficiency. In this work, we propose Fast-dLLM v2,…

Autoregressive decoding in large language models (LLMs) requires $\mathcal{O}(n)$ sequential steps for $n$ tokens, fundamentally limiting inference throughput. Recent diffusion-based LLMs (dLLMs) enable parallel token generation through…

Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development, by enabling automation. In software engineering, LLM-powered coding agents have garnered…

With the continuous advancement in the performance of large language models (LLMs), their demand for computational resources and memory has significantly increased, which poses major challenges for efficient inference on consumer-grade…

Self-consistency boosts inference-time performance by sampling multiple reasoning traces in parallel and voting. However, in constrained domains like math and code, this strategy is compute-inefficient because it samples with replacement,…

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…

Transformer language models generate text autoregressively, making inference latency proportional to the number of tokens generated. Speculative decoding reduces this latency without sacrificing output quality, by leveraging a small draft…

We present Recurrent Drafter (ReDrafter), an advanced speculative decoding approach that achieves state-of-the-art speedup for large language models (LLMs) inference. The performance gains are driven by three key aspects: (1) leveraging a…

Large Language Models (LLMs) exhibit high inference latency due to their autoregressive decoding nature. While the draft head in speculative decoding mitigates this issue, its full potential remains unexplored. In this paper, we introduce…

Despite their strong performance on reasoning tasks, large reasoning models (LRMs) often suffer from overthinking, producing unnecessarily long outputs and incurring high end-to-end latency, a significant limitation to their real-world…

Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive models for faster inference via parallel token generation. We provide a rigorous foundation for this advantage by formalizing a model of parallel…

Large language models and large multimodal models (LLMs and LMMs) deliver strong generative performance but suffer from slow decoding, a problem that becomes more severe when handling visual inputs, whose sequences typically contain many…

Diffusion language models promise parallel generation, yet still lag behind autoregressive (AR) models in quality. We stem this gap to a failure of introspective consistency: AR models agree with their own generations, while DLMs often do…

Speculative decoding accelerates LLMs by using a lightweight draft model to generate tokens autoregressively before verifying them in parallel with a larger target model. However, determining the optimal number of tokens to draft remains a…

Inference time latency has remained an open challenge for real world applications of large language models (LLMs). State-of-the-art (SOTA) speculative sampling (SpS) methods for LLMs, like EAGLE-3, use tree-based drafting to explore…