Related papers: FR-Spec: Accelerating Large-Vocabulary Language Mo…

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…

Large Language Model (LLM)-based generative recommendation has achieved notable success, yet its practical deployment is costly particularly due to excessive inference latency caused by autoregressive decoding. For lossless LLM decoding…

Reinforcement Learning (RL) has become a cornerstone for improving the performance of Large Language Models (LLMs). However, its rollout phase constitutes a significant efficiency bottleneck, mainly arising from the long-tail bubbles across…

Speculative decoding (SD) accelerates language model inference by drafting tokens from a cheap proposal model and verifying them against an expensive target model via rejection sampling. Because rejection truncates the draft block at the…

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…

Speculative decoding has become the standard approach for accelerating Large Language Model (LLM) inference. It exploits a lossless draft-then-verify procedure to circumvent the latency of autoregressive decoding, achieving impressive…

Speculative decoding accelerates large language model inference using a smaller draft model. In this paper, we establish a surprising connection between speculative decoding and channel simulation, which aims at simulating a noisy channel…

Speculative decoding accelerates large language model (LLM) inference by using a small draft model to propose candidate tokens that a larger target model verifies. A critical hyperparameter in this process is the speculation length…

Speculative reasoning has recently been proposed as a means to accelerate reasoning-intensive generation in large multimodal models, but its effectiveness is often constrained by misalignment between speculative drafts and target-verified…

Speculative decoding has emerged as a widely adopted paradigm for accelerating large language model inference, where a lightweight draft model rapidly generates candidate tokens that are then verified in parallel by a larger target model.…

Early exiting has recently emerged as a promising technique for accelerating large language models (LLMs) by effectively reducing the hardware computation and memory access. In this paper, we present SpecEE, a fast LLM inference engine with…

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…

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…

Speculative decoding is widely used in accelerating large language model (LLM) inference. In this work, we focus on the online draft model selection problem in speculative decoding. We design an algorithm that provably competes with the…

Speculative decoding accelerates large language model (LLM) inference by using a small draft model to generate candidate tokens for a larger target model to verify. The efficacy of this technique hinges on the trade-off between the time…

Speculative decoding accelerates autoregressive language model inference by verifying multiple draft tokens in parallel. However, the verification stage often becomes the dominant computational bottleneck, especially for long-context inputs…

Ensembles of generative large language models (LLMs) are a promising way to compensate for individual model limitations, integrating the strengths of different LLMs. Existing LLM ensemble methods, however, face limitations such as…

Speculative decoding accelerates LLM inference by using a smaller draft model to speculate tokens that a larger target model verifies. Verification is often the bottleneck (e.g. verification is $4\times$ slower than token generation when a…

Speculative decoding accelerates LLM inference by utilizing otherwise idle computational resources during memory-to-chip data transfer. Current speculative decoding methods typically assume a considerable amount of available computing…

This paper introduces SpecInfer, a system that accelerates generative large language model (LLM) serving with tree-based speculative inference and verification. The key idea behind SpecInfer is leveraging small speculative models to predict…