Related papers: SMART: When is it Actually Worth Expanding a Specu…

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…

We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs). RSD synergistically combines a lightweight draft model with a more powerful target…

Large language models typically generate tokens autoregressively, using each token as input for the next. Recent work on Speculative Decoding has sought to accelerate this process by employing a smaller, faster draft model to more quickly…

Speculative decoding accelerates autoregressive generation by letting a lightweight draft model propose future tokens that a larger target model then verifies in parallel. In practice, however, draft models are usually trained on broad…

Interpretable reinforcement learning policies are essential for high-stakes decision-making, yet optimizing decision tree policies in Markov Decision Processes (MDPs) remains challenging. We propose SPOT, a novel method for computing…

Large Language Models (LLMs) increasingly rely on reinforcement learning with verifiable rewards (RLVR) to elicit reliable chain-of-thought reasoning. However, the training process remains bottlenecked by the computationally expensive…

Multiple heads decoding accelerates the inference of Large Language Models (LLMs) by predicting next several tokens simultaneously. It generates and verifies multiple candidate sequences in parallel via tree attention with a fixed…

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…

Recent advances leverage post-training to enhance model reasoning performance, which typically requires costly training pipelines and still suffers from inefficient, overly lengthy outputs. We introduce Speculative Thinking, a training-free…

As Large Language Models (LLMs) become increasingly accessible to end users, an ever-growing number of inference requests are initiated from edge devices and computed on centralized GPU clusters. However, the resulting exponential growth in…

Inference latency stands as a critical bottleneck in the large-scale deployment of Large Language Models (LLMs). Speculative decoding methods have recently shown promise in accelerating inference without compromising the output…

Tree of Thoughts (ToT) enhances Large Language Model (LLM) reasoning by structuring problem-solving as a spanning tree. However, recent methods focus on search accuracy while overlooking computational efficiency. The challenges of…

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,…

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…

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…

Large language models (LLMs) are increasingly needed for interactive mobile applications, but high-quality models exceed the limited DRAM available on smartphones. Flash storage can hold larger models, yet flash-backed inference is slow…

The rise of machine learning methods on heavily resource constrained devices requires not only the choice of a suitable model architecture for the target platform, but also the optimization of the chosen model with regard to execution time…

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…

Low-latency decoding for large language models (LLMs) is crucial for applications like chatbots and code assistants, yet generating long outputs remains slow in single-query settings. Prior work on speculative decoding (which combines a…

Recently, test-time scaling has garnered significant attention from the research community, largely due to the substantial advancements of the o1 model released by OpenAI. By allocating more computational resources during the inference…