Related papers: PDTrim: Targeted Pruning for Prefill-Decode Disagg…
Large language models (LLMs) alignment aims to ensure that the behavior of LLMs meets human preferences. While collecting data from multiple fine-grained, aspect-specific preferences becomes more and more feasible, existing alignment…
Fine-tuning Large Language Models (LLMs) with downstream data is often considered time-consuming and expensive. Structured pruning methods are primarily employed to improve the inference efficiency of pre-trained models. Meanwhile, they…
Large Language Models (LLMs) pruning seeks to remove unimportant weights for inference speedup with minimal accuracy impact. However, existing methods often suffer from accuracy degradation without full-model sparsity-aware fine-tuning.…
Structured pruning is one of the representative techniques for compressing large language models (LLMs) to reduce GPU memory consumption and accelerate inference speed. It offers significant practical value in improving the efficiency of…
Recently, state-of-the-art approaches for pruning large pre-trained models (LPMs) have demonstrated that the training-free removal of non-critical residual blocks in Transformers is viable for reducing model size, achieving results that…
Video large language models (Vid-LLMs) have shown strong capabilities in understanding video content. However, their reliance on dense video token representations introduces substantial memory and computational overhead in both prefilling…
Pre-trained language models achieve superior performance but are computationally expensive. Techniques such as pruning and knowledge distillation have been developed to reduce their sizes and latencies. In this work, we propose a structured…
Recent work targeting large language models (LLMs) for code generation demonstrated that increasing the amount of training data through synthetic code generation often leads to exceptional performance. In this paper we explore data pruning…
Large language models (LLMs) enable unparalleled few- and zero-shot reasoning capabilities but at a high computational footprint. A growing assortment of methods for compression promises to reduce the computational burden of LLMs in…
Despite the superior performance, it is challenging to deploy foundation models or large language models (LLMs) due to their massive parameters and computations. While pruning is a promising technique to reduce model size and accelerate the…
This paper introduces LLM-Streamline, a pioneer work on layer pruning for large language models (LLMs). It is based on the observation that different layers have varying impacts on hidden states, enabling the identification of less…
Large Language Models (LLMs) have exhibited remarkable proficiency across a wide array of NLP tasks. However, the escalation in model size also engenders substantial deployment costs. While few efforts have explored model pruning techniques…
Large Multimodal Models (LMMs) have emerged as powerful models capable of understanding various data modalities, including text, images, and videos. LMMs encode both text and visual data into tokens that are then combined and processed by…
The evolution of Large Language Models from the Transformer architecture to models with trillions of parameters has shifted the primary bottleneck from model training to real time inference. Deploying these massive models is a complex…
Pruning is a widely used technique to reduce the size and inference cost of large language models (LLMs), but it often causes performance degradation. To mitigate this, existing restoration methods typically employ parameter-efficient…
Overparametrized transformer networks are the state-of-the-art architecture for Large Language Models (LLMs). However, such models contain billions of parameters making large compute a necessity, while raising environmental concerns. To…
With the increased demand on economy and efficiency of measurement technology, Non-Intrusive Load Monitoring (NILM) has received more and more attention as a cost-effective way to monitor electricity and provide feedback to users. Deep…
Pruning aims to reduce the number of parameters while maintaining performance close to the original network. This work proposes a novel \emph{self-distillation} based pruning strategy, whereby the representational similarity between the…
Federated fine-tuning enables privacy-preserving Large Language Model (LLM) adaptation, but its high memory cost limits participation from resource-constrained devices. We propose FedPruner, an innovative federated fine-tuning paradigm that…
Making large language models (LLMs) more efficient in memory, latency, and serving cost is crucial for edge deployment, interactive applications, and sustainable inference at scale. Pruning is a promising technique, but existing pruning…