相关论文: Training-Free Activation Sparsity in Large Languag…

Large Language Models (LLMs) exhibit significant activation sparsity, where only a subset of neurons are active for a given input. Although this sparsity presents opportunities to reduce computational cost, efficiently utilizing it requires…

Scaling autoregressive large language models (LLMs) has driven unprecedented progress but comes with vast computational costs. In this work, we tackle these costs by leveraging unstructured sparsity within an LLM's feedforward layers, the…

Deploying large language models (LLMs) on edge devices presents significant challenges due to the substantial computational overhead and memory requirements. Activation sparsification can mitigate these resource challenges by reducing the…

Deploying Large Language Models (LLMs) on edge devices remains challenging due to their quadratically increasing computations with the sequence length. Existing studies for dynamic attention pruning are designed for hardware with massively…

We introduce, Q-Sparse, a simple yet effective approach to training sparsely-activated large language models (LLMs). Q-Sparse enables full sparsity of activations in LLMs which can bring significant efficiency gains in inference. This is…

In this paper, we demonstrate how to leverage 2:4 sparsity, a popular hardware-accelerated GPU sparsity pattern, to activations to accelerate large language model training and inference. Crucially we exploit the intrinsic sparsity found in…

Large Language Models have achieved remarkable success across various natural language processing tasks, yet their high computational cost during inference remains a major bottleneck. This paper introduces Sparse Expert Activation Pruning…

Active learning (AL) accelerates scientific discovery by prioritizing the most informative experiments, but traditional machine learning (ML) models used in AL suffer from cold-start limitations and domain-specific feature engineering,…

Large Language Models (LLMs) typically come with a fixed architecture, despite growing evidence that not all layers contribute equally to every downstream task. We introduce TALE (Task-Aware Layer Elimination), an inference-time method that…

Trainings of Large Language Models are generally bottlenecked by matrix multiplications. In the Transformer architecture, a large portion of these operations happens in the Feed Forward Network (FFN), and this portion increases for larger…

Over the past few years, the explosion in sparse tensor algebra workloads has led to a corresponding rise in domain-specific accelerators to service them. Due to the irregularity present in sparse tensors, these accelerators employ a wide…

Large language models (LLMs) have demonstrated impressive capabilities across various tasks, but the billion-scale parameters pose deployment challenges. Although existing methods attempt to reduce the scale of LLMs, they require either…

Collecting high-quality labeled data for model training is notoriously time-consuming and labor-intensive for various NLP tasks. While copious solutions, such as active learning for small language models (SLMs) and prevalent in-context…

In the era of large language models (LLMs), N:M sparsity has emerged as a structured compression technique critical for accelerating inference. While prior work has primarily focused on weight sparsity, it often suffers from significant…

A key challenge in AI alignment is guiding large language models (LLMs) to follow desired behaviors at test time. Activation steering, which modifies internal model activations during inference, offers a potential solution. However, prior…

The Segment Anything Model (SAM) achieves strong open-vocabulary segmentation, but its ViT-based image encoders dominate inference latency and memory. Existing activation compression methods, such as token merging, reduce the token length…

The recent rise of Large Language Models (LLMs) has revolutionized the deep learning field. However, the desire to deploy LLMs on edge devices introduces energy efficiency and latency challenges. Recurrent LLM (R-LLM) architectures have…

Large language models (LLMs) often struggle with strict memory, latency, and power demands. To meet these demands, various forms of dynamic sparsity have been proposed that reduce compute on an input-by-input basis. These methods improve…

Large Language Models (LLMs) are difficult to fully fine-tune (e.g., with instructions or human feedback) due to their sheer number of parameters. A family of parameter-efficient sparse fine-tuning methods have proven promising in terms of…

Inducing and leveraging sparse activations during training and inference is a promising avenue for improving the computational efficiency of deep networks, which is increasingly important as network sizes continue to grow and their…