Rank and run-time aware compression of NLP Applications
Sequence model based NLP applications can be large. Yet, many applications that benefit from them run on small devices with very limited compute and storage capabilities, while still having run-time constraints. As a result, there is a need for a compression technique that can achieve significant compression without negatively impacting inference run-time and task accuracy. This paper proposes a new compression technique called Hybrid Matrix Factorization that achieves this dual objective. HMF improves low-rank matrix factorization (LMF) techniques by doubling the rank of the matrix using an intelligent hybrid-structure leading to better accuracy than LMF. Further, by preserving dense matrices, it leads to faster inference run-time than pruning or structure matrix based compression technique. We evaluate the impact of this technique on 5 NLP benchmarks across multiple tasks (Translation, Intent Detection, Language Modeling) and show that for similar accuracy values and compression factors, HMF can achieve more than 2.32x faster inference run-time than pruning and 16.77% better accuracy than LMF.
Code (0)
등록된 구현이 없습니다.
Tasks
Intent DetectionLanguage ModelingLanguage ModellingTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SigmaScale: LLM Compression with SVD-based Low-Rank Decomposition and Learned Scaling Matrices
We present SigmaScale, a method for learning auxiliary scaling matrices $S$ to aid truncated Singular Value Decomposition (SVD) based Large Language Model (LLM) compression. Instead of deriving scaling matrices analytica…
HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks
Low-rank compression is an important model compression strategy for obtaining compact neural network models. In general, because the rank values directly determine the model complexity and model accuracy, proper selectio…
GPULow-rank compressionModel CompressionLow Rank Optimization for Efficient Deep Learning: Making A Balance between Compact Architecture and Fast Training
Deep neural networks have achieved great success in many data processing applications. However, the high computational complexity and storage cost makes deep learning hard to be used on resource-constrained devices, and …
Model CompressionQuantizationBeyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning
Incorporating external knowledge in large language models (LLMs) enhances their utility across diverse applications, but existing methods have trade-offs. Retrieval-Augmented Generation (RAG) fetches evidence via similar…
RAGRetrieval-augmented GenerationBALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression
Activation-aware low-rank factorization techniques yield strong compression results but are generally confined to linear layers, while existing whitening-based theory typically makes an implicit full-rank assumption on a…
Model Compression