Related papers: Temperature-Centric Investigation of Speculative D…
Self-consistency improves reasoning by aggregating diverse stochastic samples, yet the dynamics behind its efficacy remain underexplored. We reframe self-consistency as a dynamic distributional alignment problem, revealing that decoding…
Knowledge distillation (KD) is a key technique for compressing large language models into smaller ones while preserving performance. Despite the recent traction of KD research, its effectiveness for smaller language models (LMs) and the…
Deployment of autoregressive large language models (LLMs) is costly, and as these models increase in size, the associated costs will become even more considerable. Consequently, different methods have been proposed to accelerate the token…
This technical report describes the design and training of novel speculative decoding draft models, for accelerating the inference speeds of large language models in a production environment. By conditioning draft predictions on both…
Speculative sampling is a popular technique for accelerating inference in Large Language Models by generating candidate tokens using a fast draft model and accepting or rejecting them based on the target model's distribution. While…
Knowledge Distillation (KD) is a model-agnostic technique to improve model quality while having a fixed capacity budget. It is a commonly used technique for model compression, where a larger capacity teacher model with better quality is…
As one of their many applications, large language models (LLMs) have recently shown promise in automating register transfer level (RTL) code generation. However, conventional LLM decoding strategies, originally designed for natural…
This paper explores sequence-level knowledge distillation (KD) of multilingual pre-trained encoder-decoder translation models. We argue that the teacher model's output distribution holds valuable insights for the student, beyond the…
Large language models (LLMs) have shown outstanding performance across numerous real-world tasks. However, the autoregressive nature of these models makes the inference process slow and costly. Speculative decoding has emerged as a…
Sequence-level knowledge distillation (SLKD) is a model compression technique that leverages large, accurate teacher models to train smaller, under-parameterized student models. Why does pre-processing MT data with SLKD help us train…
Speculative decoding has emerged as a promising technique to accelerate the inference of Large Language Models (LLMs) by employing a small language model to draft a hypothesis sequence, which is then validated by the LLM. The effectiveness…
Knowledge distillation (KD) is a core component in the training and deployment of modern generative models, particularly large language models (LLMs). While its empirical benefits are well documented -- enabling smaller student models to…
We propose a straightforward approach called Distillation Contrastive Decoding (DCD) to enhance the reasoning capabilities of Large Language Models (LLMs) during inference. In contrast to previous approaches that relied on smaller amateur…
Knowledge distillation (KD) is a key technique for compressing large-scale language models (LLMs), yet prevailing logit-based methods typically employ static strategies that are misaligned with the dynamic learning process of student…
Reinforcement Learning has demonstrated substantial improvements in the reasoning abilities of Large Language Models (LLMs), exhibiting significant applicability across various domains. Recent research has identified that tokens within LLMs…
Much research in recent years has focused on using empirical machine learning approaches to extract useful insights on the structure-property relationships of superconductor material. Notably, these approaches are bringing extreme benefits…
Diffusion Policy (DP) excels in embodied control but suffers from high inference latency and computational cost due to multiple iterative denoising steps. The temporal complexity of embodied tasks demands a dynamic and adaptable computation…
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…
LLMs have low GPU efficiency and high latency due to autoregressive decoding. Speculative decoding (SD) mitigates this using a small draft model to speculatively generate multiple tokens, which are then verified in parallel by a target…
The concept of knowledge distillation (KD) describes the training of a student model from a teacher model and is a widely adopted technique in deep learning. However, it is still not clear how and why distillation works. Previous studies…