Related papers: AutoJudge: Judge Decoding Without Manual Annotatio…

Accurate document retrieval is crucial for the success of retrieval-augmented generation (RAG) applications, including open-domain question answering and code completion. While large language models (LLMs) have been employed as dense…

Model-based evaluation is at the heart of successful model development -- as a reward model for training, and as a replacement for human evaluation. To train such evaluators, the standard approach is to collect a large amount of human…

Large language models (LLMs) are increasingly used as automated judges to evaluate recommendation systems, search engines, and other subjective tasks, where relying on human evaluators can be costly, time-consuming, and unscalable. LLMs…

Speculative decoding is an emerging technique that accelerates large language model (LLM) inference by allowing a smaller draft model to predict multiple tokens in advance, which are then verified or corrected by a larger target model. In…

As large language models gain widespread adoption, running them efficiently becomes crucial. Recent works on LLM inference use speculative decoding to achieve extreme speedups. However, most of these works implicitly design their algorithms…

The computational cost of training multimodal large language models (MLLMs) grows rapidly with the number of processed tokens. Existing efficiency methods mainly target inference via token reduction or merging, offering limited benefits…

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…

Speculative Decoding has emerged as a popular technique for accelerating inference in Large Language Models. However, most existing approaches yield only modest improvements in production serving systems. Methods that achieve substantial…

In this paper, we introduce a simple training-free technique to improve the performance of drafter-based speculative decoding (SpD) methods that incorporates language modeling head (LM head) during drafting process. A drafter-based…

A Large Language Model (LLM) as judge evaluates the quality of victim Machine Learning (ML) models, specifically LLMs, by analyzing their outputs. An LLM as judge is the combination of one model and one specifically engineered judge prompt…

Prompt engineering plays a critical role in adapting large language models (LLMs) to complex reasoning and labeling tasks without the need for extensive fine-tuning. In this paper, we propose a novel prompt optimization pipeline for frame…

We propose a novel speculative decoding method tailored for multi-sample reasoning scenarios, such as self-consistency and Best-of-N sampling. Our method exploits the intrinsic consensus of parallel generation paths to synthesize…

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…

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…

Speculative decoding has proven to be an efficient solution to large language model (LLM) inference, where the small drafter predicts future tokens at a low cost, and the target model is leveraged to verify them in parallel. However, most…

Vision-language Models (VLMs) have made significant strides in visual understanding and query response generation, but often face challenges of high computational cost and inference latency due to autoregressive decoding. In this work, we…

Retrieval-Augmented Generation (RAG) has proven its effectiveness in alleviating hallucinations for Large Language Models (LLMs). However, existing automated evaluation metrics cannot fairly evaluate the outputs generated by RAG models…

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…

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…

Large language models achieve impressive performance across diverse tasks but exhibit high inference latency due to their large parameter sizes. While quantization reduces model size, it often leads to performance degradation compared to…