Related papers: EAGLE: Speculative Sampling Requires Rethinking Fe…

Large language models (LLMs) have shown remarkable capabilities in various natural language understanding tasks. With only a few demonstration examples, these LLMs can quickly adapt to target tasks without expensive gradient updates. Common…

Text generation with Large Language Models (LLMs) is known to be memory bound due to the combination of their auto-regressive nature, huge parameter counts, and limited memory bandwidths, often resulting in low token rates. Speculative…

Large language models often generate confident but incorrect answers rather than abstaining when uncertain. This problem is particularly acute for small language models (SLMs), where computational constraints and autonomous operation…

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…

Large Language Models (LLMs) deliver exceptional performance across natural language tasks but demand substantial computational resources, limiting their deployment on resource-constrained edge devices. Existing compression techniques, such…

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…

The proliferation of Large Language Models (LLMs) with varying capabilities and costs has created a need for efficient model selection in AI systems. LLM routers address this need by dynamically choosing the most suitable model for a given…

Audio-visual target speaker extraction (AV-TSE) models primarily rely on visual cues from the target speaker. However, humans also leverage linguistic knowledge, such as syntactic constraints, next word prediction, and prior knowledge of…

Large Language Models can generate synthetic survey responses at low cost, but their accuracy varies unpredictably across questions. We study the design problem of allocating a fixed budget of human respondents across estimation tasks when…

Large language model (LLM) decoding involves generating a sequence of tokens based on a given context, where each token is predicted one at a time using the model's learned probabilities. The typical autoregressive decoding method requires…

Large language models (LLMs) achieve strong average performance yet remain unreliable at the instance level, with frequent hallucinations, brittle failures, and poorly calibrated confidence. We study reliability through the lens of…

LLM deployment on resource-constrained edge devices faces severe latency constraints, particularly in real-time applications where delayed responses can compromise safety or usability. Among many approaches to mitigate the inefficiencies of…

Cascades and speculative decoding are two common approaches to improving language models' inference efficiency. Both approaches involve interleaving models of different sizes, but via fundamentally distinct mechanisms: cascades employ a…

Recent reasoning models, such as OpenAI's O1 series, have demonstrated exceptional performance on complex reasoning tasks and revealed new test-time scaling laws. Inspired by this, many people have been studying how to train models to…

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…

The efficiency of large language models (LLMs) is fundamentally limited by their sequential, token-by-token generation process. We argue that overcoming this bottleneck requires a new design axis for LLM scaling: increasing the semantic…

Speculative decoding is an effective and lossless method for Large Language Model (LLM) inference acceleration. It employs a smaller model to generate a draft token sequence, which is then verified by the original base model. In multi-GPU…

While Large Language Models (LLMs) have found success in real-world applications, their underlying explanatory process is still poorly understood. This paper proposes IBE-Eval, a framework inspired by philosophical accounts on Inference to…

Large language models (LLMs) exhibit remarkable reasoning capabilities across diverse downstream tasks. However, their autoregressive nature leads to substantial inference latency, posing challenges for real-time applications. Speculative…

Speculative decoding is a powerful technique that attempts to circumvent the autoregressive constraint of modern Large Language Models (LLMs). The aim of speculative decoding techniques is to improve the average inference time of a large,…