相关论文: DeepGEMM: Accelerated Ultra Low-Precision Inferenc…

Currently, deep neural networks are deployed on low-power portable devices by first training a full-precision model using powerful hardware, and then deriving a corresponding low-precision model for efficient inference on such systems.…

The computational and memory challenges of large language models (LLMs) have sparked several optimization approaches towards their efficient implementation. While prior LLM-targeted quantization, and prior works on sparse acceleration have…

In this paper we present a simple and computationally efficient quantization scheme that enables us to reduce the resolution of the parameters of a neural network from 32-bit floating point values to 8-bit integer values. The proposed…

Current low-precision quantization algorithms often have the hidden cost of conversion back and forth from floating point to quantized integer values. This hidden cost limits the latency improvement realized by quantizing Neural Networks.…

Although weight and activation quantization is an effective approach for Deep Neural Network (DNN) compression and has a lot of potentials to increase inference speed leveraging bit-operations, there is still a noticeable gap in terms of…

We propose a cluster-based quantization method to convert pre-trained full precision weights into ternary weights with minimal impact on the accuracy. In addition, we also constrain the activations to 8-bits thus enabling sub 8-bit full…

Large language models (LLMs) have transformed artificial intelligence, but their computational requirements remain prohibitive for most users. Standard inference demands expensive datacenter GPUs or cloud API access, leaving over one…

Sequence alignment is a memory bound computation whose performance in modern systems is limited by the memory bandwidth bottleneck. Processing-in-memory architectures alleviate this bottleneck by providing the memory with computing…

On-device Deep Neural Network (DNN) inference consumes significant computing resources and development efforts. To alleviate that, we propose LUT-NN, the first system to empower inference by table lookup, to reduce inference cost. LUT-NN…

We propose a novel 2-stage sub 8-bit quantization aware training algorithm for all components of a 250K parameter feedforward, streaming, state-free keyword spotting model. For the 1st-stage, we adapt a recently proposed quantization…

Deploying Vision-Language Models (VLMs) on edge devices (e.g., smartphones and robots) is crucial for enabling low-latency and privacy-preserving intelligent applications. Given the resource constraints of these devices, quantization offers…

We introduce a method to train Quantized Neural Networks (QNNs) --- neural networks with extremely low precision (e.g., 1-bit) weights and activations, at run-time. At train-time the quantized weights and activations are used for computing…

This paper advocates for an intertwined design of the dense linear algebra software stack that breaks down the strict barriers between the high-level, blocked algorithms in LAPACK (Linear Algebra PACKage) and the low-level,…

The deployment of large language models (LLMs) is frequently hindered by prohibitive memory and computational requirements. While quantization mitigates these bottlenecks, maintaining model fidelity in the sub-1-bit regime remains a…

General matrix multiplication (GEMM) is a ubiquitous computing kernel/algorithm for data processing in diverse applications, including artificial intelligence (AI) and deep learning (DL). Recent shift towards edge computing has inspired…

Large language models have been widely adopted but require significant GPU memory for inference. We develop a procedure for Int8 matrix multiplication for feed-forward and attention projection layers in transformers, which cut the memory…

Specialized edge accelerators rely on low-bit quantization, but vendor compilers differ in scaling, clipping, and kernel support, often as black boxes. The same floating-point (FP) checkpoint can therefore yield inconsistent accuracy across…

Deep neural networks (DNNs) have demonstrated their effectiveness in a wide range of computer vision tasks, with the state-of-the-art results obtained through complex and deep structures that require intensive computation and memory.…

This paper aims at rapid deployment of the state-of-the-art deep neural networks (DNNs) to energy efficient accelerators without time-consuming fine tuning or the availability of the full datasets. Converting DNNs in full precision to…

Large Language Model (LLM) inference requires substantial computational resources, yet CPU-based inference remains essential for democratizing AI due to the widespread availability of CPUs compared to specialized accelerators. However,…