Related papers: Speculative Decoding with a Speculative Vocabulary

Large language models (LLMs) underpin interactive multimedia applications such as captioning, retrieval, recommendation, and creative content generation, yet their autoregressive decoding incurs substantial latency. Speculative decoding…

Large language models achieve strong machine translation quality but incur high inference cost and latency, posing challenges for simultaneous translation. Re-translation provides a practical solution for off-the-shelf LLMs by repeatedly…

Large Language Models (LLMs) present a critical trade-off between inference quality and computational cost: larger models offer superior capabilities but incur significant latency, while smaller models are faster but less powerful. Existing…

Speculative decoding (SD) has been shown to reduce the latency of autoregressive decoding (AD) by 2-3x for small batch sizes. However, increasing throughput and therefore reducing the cost per token requires decoding with large batch sizes.…

Speculative decoding accelerates generation by drafting candidates and verifying them in parallel, yet state-of-the-art drafters (e.g., EAGLE) still require N sequential passes to propose N tokens. We present FastEagle, a non-autoregressive…

Speculative decoding is an effective method for accelerating inference of large language models (LLMs) by employing a small draft model to predict the output of a target model. However, when adapting speculative decoding to domain-specific…

Long-context large language model (LLM) inference has become the norm for today's AI applications. However, it is severely bottlenecked by the increasing memory demands of its KV cache. Previous works have shown that self-speculative…

As large language models (LLMs) scale up, accuracy improves, but the autoregressive (AR) nature of decoding increases latency since each token requires a serial forward pass. Speculative decoding addresses this by employing a fast drafter…

Speculative decoding (SD), where an extra draft model is employed to provide multiple draft tokens first, and then the original target model verifies these tokens in parallel, has shown great power for LLM inference acceleration. However,…

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…

Speculative decoding is a powerful technique for reducing the latency of Large Language Models (LLMs), offering a fault-tolerant framework that enables the use of highly compressed draft models. In this work, we introduce Self-Distilled…

Autoregressive Language Models instantiate a factorized likelihood over token sequences, yet their strictly sequential decoding process imposes an intrinsic lower bound on inference latency. This bottleneck has emerged as a central obstacle…

Deploying large language models (LLMs) in mobile and edge computing environments is constrained by limited on-device resources, scarce wireless bandwidth, and frequent model evolution. Although edge-cloud collaborative inference with…

LLM serving platforms are increasingly deployed as multi-model cloud systems, where user demand is often long-tailed: a few popular large models receive most requests, while many smaller tail models remain underutilized. We propose…

Speculative decoding accelerates large language model (LLM) inference by using a smaller draft model to propose tokens, which are then verified by a larger target model. However, selecting an optimal speculation length is critical for…

Striking an optimal balance between minimal drafting latency and high speculation accuracy to enhance the inference speed of Large Language Models remains a significant challenge in speculative decoding. In this paper, we introduce Falcon,…

Speculative Decoding promises to accelerate the inference of Large Language Models, yet its efficacy often degrades in production-grade serving. Existing evaluations typically overlook the compute-bound nature of high-concurrency regimes,…

With the increasingly giant scales of (causal) large language models (LLMs), the inference efficiency comes as one of the core concerns along the improved performance. In contrast to the memory footprint, the latency bottleneck seems to be…

Parallel Speculative Decoding (PSD) accelerates traditional Speculative Decoding (SD) by overlapping draft generation with verification. However, it remains hampered by two fundamental challenges: (1) a theoretical speedup ceiling dictated…

Large reasoning language models such as OpenAI-o1 and Deepseek-R1 have recently attracted widespread attention due to their impressive task-solving abilities. However, the enormous model size and the generation of lengthy thought chains…