Minsik Cho
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Minsik Cho has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Saurabh N. Adya
Apple, Cupertino, CA, USA
2 shared publications - Carlo C. Del Mundo
Apple, Cupertino, CA, USA
1 shared publication - David Kung
Department of Neurosurgery, University of Pennsylvania, Philadelphia, Pennsylvania, USA
1 shared publication - Devang Naik
Apple, Cupertino, CA, USA
1 shared publication Dheeraj Sreedhar
IBM Research
1 shared publication- Keivan A. Vahid
Apple, Cupertino, CA, USA
1 shared publication
Latest Publications
- 7 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Computer Architecture Letters
- Vol. 23 (1) , 37-40
eDKM: An Efficient and Accurate Train-Time Weight Clustering for Large Language Models
The size of LLMs (i.e., billions of parameters) requires highly effective compression to fit into storage-limited devices. Among many compression techniques, weight-clustering, a form of non-linear quantization, is one of the leading candidates for LLM compression, and supported by modern smartphones. Yet, its training overhead is prohibitively significant for LLM fine-tuning. Especially, Differentiable KMeans Clustering, or DKM, has shown the state-of-the-art trade-off between compression ratio and accuracy regression, but its large memory complexity makes it nearly impossible to apply to train-time LLM compression. In this paper, we propose a memory-efficient DKM implementation, eDKM powered by novel techniques to reduce the memory footprint of DKM by orders of magnitudes. For a given tensor to be saved on CPU for the backward pass of DKM, we compressed the tensor by applying uniquification and sharding after checking if there is no duplicated tensor previously copied to CPU. Our experimental results demonstrate that eDKM can fine-tune and compress a pretrained LLaMA 7B model from 12.6 GB to 2.5 GB (3bit/weight) with the Alpaca dataset by reducing the train-time memory footprint of a decoder layer by 130×, while delivering good accuracy on broader LLM benchmarks (i.e., 77.7% for PIQA, 66.1% for Winograde, and so on).
- 7 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Computer Architecture Letters
- Vol. 23 (1) , 37-40
eDKM: An Efficient and Accurate Train-Time Weight Clustering for Large Language Models
The size of LLMs (i.e., billions of parameters) requires highly effective compression to fit into storage-limited devices. Among many compression techniques, weight-clustering, a form of non-linear quantization, is one of the leading candidates for LLM compression, and supported by modern smartphones. Yet, its training overhead is prohibitively significant for LLM fine-tuning. Especially, Differentiable KMeans Clustering, or DKM, has shown the state-of-the-art trade-off between compression ratio and accuracy regression, but its large memory complexity makes it nearly impossible to apply to train-time LLM compression. In this paper, we propose a memory-efficient DKM implementation, eDKM powered by novel techniques to reduce the memory footprint of DKM by orders of magnitudes. For a given tensor to be saved on CPU for the backward pass of DKM, we compressed the tensor by applying uniquification and sharding after checking if there is no duplicated tensor previously copied to CPU. Our experimental results demonstrate that eDKM can fine-tune and compress a pretrained LLaMA 7B model from 12.6 GB to 2.5 GB (3bit/weight) with the Alpaca dataset by reducing the train-time memory footprint of a decoder layer by 130×, while delivering good accuracy on broader LLM benchmarks (i.e., 77.7% for PIQA, 66.1% for Winograde, and so on).
- Open Access
DKM: Differentiable K-Means Clustering Layer for Neural Network Compression
Deep neural network (DNN) model compression for efficient on-device inference is becoming increasingly important to reduce memory requirements and keep user data on-device. To this end, we propose a novel differentiable k-means clustering layer (DKM) and its application to train-time weight clustering-based DNN model compression. DKM casts k-means clustering as an attention problem and enables joint optimization of the DNN parameters and clustering centroids. Unlike prior works that rely on additional regularizers and parameters, DKM-based compression keeps the original loss function and model architecture fixed. We evaluated DKM-based compression on various DNN models for computer vision and natural language processing (NLP) tasks. Our results demonstrate that DKM delivers superior compression and accuracy trade-off on ImageNet1k and GLUE benchmarks. For example, DKM-based compression can offer 74.5% top-1 ImageNet1k accuracy on ResNet50 DNN model with 3.3MB model size (29.4x model compression factor). For MobileNet-v1, which is a challenging DNN to compress, DKM delivers 63.9% top-1 ImageNet1k accuracy with 0.72 MB model size (22.4x model compression factor). This result is 6.8% higher top-1accuracy and 33% relatively smaller model size than the current state-of-the-art DNN compression algorithms. Additionally, DKM enables compression of DistilBERT model by 11.8x with minimal (1.1%) accuracy loss on GLUE NLP benchmarks.
Open AccessDKM: Differentiable K-Means Clustering Layer for Neural Network Compression
Deep neural network (DNN) model compression for efficient on-device inference is becoming increasingly important to reduce memory requirements and keep user data on-device. To this end, we propose a novel differentiable k-means clustering layer (DKM) and its application to train-time weight clustering-based DNN model compression. DKM casts k-means clustering as an attention problem and enables joint optimization of the DNN parameters and clustering centroids. Unlike prior works that rely on additional regularizers and parameters, DKM-based compression keeps the original loss function and model architecture fixed. We evaluated DKM-based compression on various DNN models for computer vision and natural language processing (NLP) tasks. Our results demonstrate that DKM delivers superior compression and accuracy trade-off on ImageNet1k and GLUE benchmarks. For example, DKM-based compression can offer 74.5% top-1 ImageNet1k accuracy on ResNet50 DNN model with 3.3MB model size (29.4x model compression factor). For MobileNet-v1, which is a challenging DNN to compress, DKM delivers 63.9% top-1 ImageNet1k accuracy with 0.72 MB model size (22.4x model compression factor). This result is 6.8% higher top-1accuracy and 33% relatively smaller model size than the current state-of-the-art DNN compression algorithms. Additionally, DKM enables compression of DistilBERT model by 11.8x with minimal (1.1%) accuracy loss on GLUE NLP benchmarks.
- Open Access
PowerAI DDL
As deep neural networks become more complex and input datasets grow larger, it can take days or even weeks to train a deep neural network to the desired accuracy. Therefore, distributed Deep Learning at a massive scale is a critical capability, since it offers the potential to reduce the training time from weeks to hours. In this paper, we present a software-hardware co-optimized distributed Deep Learning system that can achieve near-linear scaling up to hundreds of GPUs. The core algorithm is a multi-ring communication pattern that provides a good tradeoff between latency and bandwidth and adapts to a variety of system configurations. The communication algorithm is implemented as a library for easy use. This library has been integrated into Tensorflow, Caffe, and Torch. We train Resnet-101 on Imagenet 22K with 64 IBM Power8 S822LC servers (256 GPUs) in about 7 hours to an accuracy of 33.8 % validation accuracy. Microsoft's ADAM and Google's DistBelief results did not reach 30 % validation accuracy for Imagenet 22K. Compared to Facebook AI Research's recent paper on 256 GPU training, we use a different communication algorithm, and our combined software and hardware system offers better communication overhead for Resnet-50. A PowerAI DDL enabled version of Torch completed 90 epochs of training on Resnet 50 for 1K classes in 50 minutes using 64 IBM Power8 S822LC servers (256 GPUs).
Open AccessPowerAI DDL
As deep neural networks become more complex and input datasets grow larger, it can take days or even weeks to train a deep neural network to the desired accuracy. Therefore, distributed Deep Learning at a massive scale is a critical capability, since it offers the potential to reduce the training time from weeks to hours. In this paper, we present a software-hardware co-optimized distributed Deep Learning system that can achieve near-linear scaling up to hundreds of GPUs. The core algorithm is a multi-ring communication pattern that provides a good tradeoff between latency and bandwidth and adapts to a variety of system configurations. The communication algorithm is implemented as a library for easy use. This library has been integrated into Tensorflow, Caffe, and Torch. We train Resnet-101 on Imagenet 22K with 64 IBM Power8 S822LC servers (256 GPUs) in about 7 hours to an accuracy of 33.8 % validation accuracy. Microsoft's ADAM and Google's DistBelief results did not reach 30 % validation accuracy for Imagenet 22K. Compared to Facebook AI Research's recent paper on 256 GPU training, we use a different communication algorithm, and our combined software and hardware system offers better communication overhead for Resnet-50. A PowerAI DDL enabled version of Torch completed 90 epochs of training on Resnet 50 for 1K classes in 50 minutes using 64 IBM Power8 S822LC servers (256 GPUs).