SmartQuant: CXL-based AI Model Store in Support of Runtime Configurable Weight Quantization

• URL: http://arxiv.org/abs/2407.15866v2
• Date: Sat, 17 Aug 2024 19:44:41 GMT
• Title: SmartQuant: CXL-based AI Model Store in Support of Runtime Configurable Weight Quantization
• Authors: Rui Xie, Asad Ul Haq, Linsen Ma, Krystal Sun, Sanchari Sen, Swagath Venkataramani, Liu Liu, Tong Zhang,
• Abstract summary: Recent studies have revealed that during the inference on generative AI models, the importance of different weights exhibits substantial context-dependent variations. This naturally manifests a promising potential of adaptively configuring weight quantization to improve the generative AI inference efficiency. Motivated by the rapidly maturing CXL ecosystem, this work develops a CXL-based design solution to fill this gap.
• Score: 14.141233153682876
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent studies have revealed that, during the inference on generative AI models such as transformer, the importance of different weights exhibits substantial context-dependent variations. This naturally manifests a promising potential of adaptively configuring weight quantization to improve the generative AI inference efficiency. Although configurable weight quantization can readily leverage the hardware support of variable-precision arithmetics in modern GPU and AI accelerators, little prior research has studied how one could exploit variable weight quantization to proportionally improve the AI model memory access speed and energy efficiency. Motivated by the rapidly maturing CXL ecosystem, this work develops a CXL-based design solution to fill this gap. The key is to allow CXL memory controllers play an active role in supporting and exploiting runtime configurable weight quantization. Using transformer as a representative generative AI model, we carried out experiments that well demonstrate the effectiveness of the proposed design solution.

Related papers

• Balance of Number of Embedding and their Dimensions in Vector Quantization [11.577770138594436]
  This study examines the balance between the codebook sizes and dimensions of embeddings in the Vector Quantized Variational Autoencoder (VQ-VAE) architecture. We propose a novel adaptive dynamic quantization approach, underpinned by the Gumbel-Softmax mechanism.
  arXiv  Detail & Related papers  (2024-07-06T03:07:31Z)
• Designing variational ansatz for quantum-enabled simulation of non-unitary dynamical evolution -- an excursion into Dicke supperradiance [7.977318221782395]
  We employ the unrestricted vectorization variant of AVQD to simulate and benchmark various non-unitarily evolving systems. We show an efficient decomposition scheme for the ansatz used, which can extend its applications to a wide range of other open quantum system scenarios. Our successful demonstrations pave the way for utilizing this adaptive variational technique to study complex systems in chemistry and physics.
  arXiv  Detail & Related papers  (2024-03-07T16:57:24Z)
• WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More [55.0856305773081]
  Large Language Models (LLMs) face significant deployment challenges due to their substantial memory requirements and the computational demands of auto-regressive text generation process. This paper addresses these challenges by focusing on the quantization of LLMs, a technique that reduces memory consumption by converting model parameters and activations into low-bit integers.
  arXiv  Detail & Related papers  (2024-02-19T11:33:21Z)
• EdgeQAT: Entropy and Distribution Guided Quantization-Aware Training for the Acceleration of Lightweight LLMs on the Edge [40.85258685379659]
  Post-Training Quantization (PTQ) methods degrade in quality when quantizing weights, activations, and KV cache together to below 8 bits. Many Quantization-Aware Training (QAT) works quantize model weights, leaving the activations untouched, which do not fully exploit the potential of quantization for inference acceleration on the edge. We propose EdgeQAT, the Entropy and Distribution Guided QAT for the optimization of lightweight LLMs to achieve inference acceleration on Edge devices.
  arXiv  Detail & Related papers  (2024-02-16T16:10:38Z)
• Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers [10.566264033360282]
  Post-training quantization (PTQ) has emerged as a promising solution for deploying hyper-scale models on edge devices such as mobile and TVs. In this paper, we propose a novel PTQ algorithm that balances accuracy and efficiency.
  arXiv  Detail & Related papers  (2024-02-14T05:58:43Z)
• Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting [13.270381125055275]
  We propose a coarse & fine weight splitting (CFWS) method to reduce quantization error of weight. We develop an improved KL metric to determine optimal quantization scales for activation. For example, the quantized RepVGG-A1 model exhibits a mere 0.3% accuracy loss.
  arXiv  Detail & Related papers  (2023-12-17T02:31:20Z)
• OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models [57.27101446992148]
  Large language models (LLMs) have revolutionized natural language processing tasks. Recent post-training quantization (PTQ) methods are effective in reducing memory footprint and improving the computational efficiency of LLM. We introduce an Omnidirectionally calibrated Quantization technique for LLMs, which achieves good performance in diverse quantization settings.
  arXiv  Detail & Related papers  (2023-08-25T02:28:35Z)
• Weight Re-Mapping for Variational Quantum Algorithms [54.854986762287126]
  We introduce the concept of weight re-mapping for variational quantum circuits (VQCs) We employ seven distinct weight re-mapping functions to assess their impact on eight classification datasets. Our results indicate that weight re-mapping can enhance the convergence speed of the VQC.
  arXiv  Detail & Related papers  (2023-06-09T09:42:21Z)
• Improving Convergence for Quantum Variational Classifiers using Weight Re-Mapping [60.086820254217336]
  In recent years, quantum machine learning has seen a substantial increase in the use of variational quantum circuits (VQCs) We introduce weight re-mapping for VQCs, to unambiguously map the weights to an interval of length $2pi$. We demonstrate that weight re-mapping increased test accuracy for the Wine dataset by $10%$ over using unmodified weights.
  arXiv  Detail & Related papers  (2022-12-22T13:23:19Z)
• Vertical Layering of Quantized Neural Networks for Heterogeneous Inference [57.42762335081385]
  We study a new vertical-layered representation of neural network weights for encapsulating all quantized models into a single one. We can theoretically achieve any precision network for on-demand service while only needing to train and maintain one model.
  arXiv  Detail & Related papers  (2022-12-10T15:57:38Z)
• BiTAT: Neural Network Binarization with Task-dependent Aggregated Transformation [116.26521375592759]
  Quantization aims to transform high-precision weights and activations of a given neural network into low-precision weights/activations for reduced memory usage and computation. Extreme quantization (1-bit weight/1-bit activations) of compactly-designed backbone architectures results in severe performance degeneration. This paper proposes a novel Quantization-Aware Training (QAT) method that can effectively alleviate performance degeneration.
  arXiv  Detail & Related papers  (2022-07-04T13:25:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.