相关论文: Batch Speculative Decoding Done Right

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…

Reasoning models excel by generating long chain-of-thoughts, but decoding the resulting thousands of tokens is slow. Token-level speculative decoding (SD) helps, but its benefit is capped, because the chance that an entire $\gamma$-token…

Auto-regressive decoding in Large Language Models (LLMs) is inherently memory-bound: every generation step requires loading the model weights and intermediate results from memory (e.g., High-Bandwidth Memory (HBM) for GPU servers), making…

Speculative decoding accelerates autoregressive inference by drafting candidate tokens with a fast model and verifying them in parallel with the target. Self-speculative methods avoid the need for an external drafter but have been studied…

Speculative decoding is an effective technique for accelerating large language model inference by drafting multiple tokens in parallel. In practice, its speedup is often bottlenecked by a rigid verification step that strictly enforces the…

Speculative decoding (SD) has become a popular technique to accelerate Large Language Model (LLM) inference, yet its real-world effectiveness remains unclear as prior evaluations rely on research prototypes and unrealistically small batch…

Large language models (LLMs) deliver impressive generation quality, but incur very high inference cost because each output token is generated auto-regressively through all model layers. Early-exit based self-speculative decoding (EESD) has…

We introduce PARSE (PArallel pRefix Speculative Engine), a speculative generation framework that accelerates large language model (LLM) inference by parallelizing prefix verification on a semantic level. Existing speculative decoding…

Speculative decoding is a promising approach for accelerating large language models. The primary idea is to use a lightweight draft model to speculate the output of the target model for multiple subsequent timesteps, and then verify them in…

Modern Large Language Models achieve impressive reasoning capabilities with long Chain of Thoughts, but they incur substantial computational cost during inference, and this motivates techniques to improve the performance-cost ratio. Among…

Speculative decoding, which combines a draft model with a target model, has emerged as an effective approach to accelerate large language model (LLM) inference. However, existing methods often face a trade-off between the acceptance rate…

Autoregressive language models suffer from high inference latency due to their sequential decoding nature. Speculative decoding (SD) mitigates this by employing a lightweight draft model to propose candidate tokens, which are selectively…

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…

Semantic code search has been widely adopted in both academia and industry. These approaches embed natural-language queries and code snippets into a shared embedding space and retrieve results based on vector similarity. Despit strong…

Speculative decoding (SD) accelerates large language model inference by using a smaller draft model to propose draft tokens that are subsequently verified by a larger target model. However, the performance of standard SD is often limited by…

Efficient and accurate decoding of quantum error-correcting codes is essential for fault-tolerant quantum computation, however, it is challenging due to the degeneracy of errors, the complex code topology, and the large space for logical…

Speculative Decoding is a widely used technique to speed up inference for Large Language Models (LLMs) without sacrificing quality. When performing inference, speculative decoding uses a smaller draft model to generate speculative tokens…

Generative Large Language Models (LLMs) based on the Transformer architecture have recently emerged as a dominant foundation model for a wide range of Natural Language Processing tasks. Nevertheless, their application in real-time scenarios…

Verification is a key bottleneck in improving inference speed while maintaining distribution fidelity in Speculative Decoding. Recent work has shown that sequence-level verification leads to a higher number of accepted tokens compared to…

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…