Related papers: E-Sparse: Boosting the Large Language Model Infere…

Pruning, the task of sparsifying deep neural networks, received increasing attention recently. Although state-of-the-art pruning methods extract highly sparse models, they neglect two main challenges: (1) the process of finding these sparse…

Long Short-Term Memory (LSTM) has achieved state-of-the-art performances on a wide range of tasks. Its outstanding performance is guaranteed by the long-term memory ability which matches the sequential data perfectly and the gating…

Neural Networks can be effectively compressed through pruning, significantly reducing storage and compute demands while maintaining predictive performance. Simple yet effective methods like magnitude pruning remove less important parameters…

Large language model (LLM) training and finetuning are often bottlenecked by limited GPU memory. While existing projection-based optimization methods address this by projecting gradients into a lower-dimensional subspace to reduce optimizer…

EIE proposed to accelerate pruned and compressed neural networks, exploiting weight sparsity, activation sparsity, and 4-bit weight-sharing in neural network accelerators. Since published in ISCA'16, it opened a new design space to…

Sparsity is a well-studied technique for compressing deep neural networks (DNNs) without compromising performance. In deep reinforcement learning (DRL), neural networks with up to 5% of their original weights can still be trained with…

Large language models (LLMs) have emerged as a powerful foundation for intelligent reasoning and decision-making, demonstrating substantial impact across a wide range of domains and applications. However, their massive parameter scales and…

We demonstrate that unstructured sparsity significantly improves KV cache compression for LLMs, enabling sparsity levels up to 70% without compromising accuracy or requiring fine-tuning. We conduct a systematic exploration of pruning…

Small language models (SLMs) have attracted considerable attention from both academia and industry due to their broad range of applications in edge devices. To obtain SLMs with strong performance, conventional approaches either pre-train…

Efficient inference of Deep Neural Networks (DNNs) on resource-constrained edge devices is essential. Quantization and sparsity are key techniques that translate to repetition and sparsity within tensors at the hardware-software interface.…

Network pruning can reduce the high computation cost of deep neural network (DNN) models. However, to maintain their accuracies, sparse models often carry randomly-distributed weights, leading to irregular computations. Consequently, sparse…

Deep learning drives a new wave in computing systems and triggers the automation of increasingly complex problems. In particular, Large Language Models (LLMs) have significantly advanced cognitive tasks, often matching or even surpassing…

Instruction tuning has optimized the specialized capabilities of large language models (LLMs), but it often requires extensive datasets and prolonged training times. The challenge lies in developing specific capabilities by identifying…

The success of DNN pruning has led to the development of energy-efficient inference accelerators that support pruned models with sparse weight and activation tensors. Because the memory layouts and dataflows in these architectures are…

Sparse Mixture of Experts (MoE) large language models (LLMs) are gradually becoming the mainstream approach for ultra-large-scale models. Existing optimization efforts for MoE models have focused primarily on coarse-grained MoE…

Large language models (LLMs) are useful in many NLP tasks and become more capable with size, with the best open-source models having over 50 billion parameters. However, using these 50B+ models requires high-end hardware, making them…

As large language models (LLMs) continue to support increasingly longer contexts, the memory demand for key-value (KV) caches during decoding grows rapidly, becoming a critical bottleneck in both GPU memory capacity and PCIe bandwidth.…

Large language models (LLMs) encode a diverse range of linguistic features within their latent representations, which can be harnessed to steer their output toward specific target characteristics. In this paper, we modify the internal…

Pruning large language models (LLMs) is a promising solution for reducing model sizes and computational complexity while preserving performance. Traditional layer-wise pruning methods often adopt a uniform sparsity approach across all…

This paper presents a Spatial Re-parameterization (SpRe) method for the N:M sparsity. SpRe stems from an observation regarding the restricted variety in spatial sparsity of convolution kernels presented in N:M sparsity compared with…