SLaNC: Static LayerNorm Calibration

• URL: http://arxiv.org/abs/2410.10553v1
• Date: Mon, 14 Oct 2024 14:32:55 GMT
• Title: SLaNC: Static LayerNorm Calibration
• Authors: Mahsa Salmani, Nikita Trukhanov, Ilya Soloveychik,
• Abstract summary: Quantization to lower precision formats naturally poses a number of challenges caused by the limited range of the available value representations. In this article, we propose a computationally-efficient scaling technique that can be easily applied to Transformer models during inference. Our method suggests a straightforward way of scaling the LayerNorm inputs based on the static weights of the immediately preceding linear layers.
• Score: 1.2016264781280588
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The ever increasing sizes of Large Language Models (LLMs) beyond hundreds of billions of parameters have generated enormous pressure on the manufacturers of dedicated hardware accelerators and made the innovative design of the latter one of the most rapidly expanding fields of the AI industry. Various approaches have been explored to enable efficient and accurate processing of LLMs on the available accelerators given their computational and storage limitations. Among these, various quantization techniques have become the main focus of the community as a means of reducing the compute, communication and storage requirements. Quantization to lower precision formats naturally poses a number of challenges caused by the limited range of the available value representations. When it comes to processing the popular Transformer models on hardware, one of the main issues becomes calculation of the LayerNorm simply because accumulation of the variance requires a much wider dynamic range than the hardware enables. In this article, we address this matter and propose a computationally-efficient scaling technique that can be easily applied to Transformer models during inference. Our method suggests a straightforward way of scaling the LayerNorm inputs based on the static weights of the immediately preceding linear layers. The scaling factors are computed offline, based solely on the linear layer weights, hence no latency or computational overhead is added during inference. Most importantly, our technique ensures that no numerical issues such as overflow or underflow could happen during the compute. This approach offers smooth, accurate and resource-effective inference across a wide range of hardware architectures. The article provides theoretical justification as well as supporting numerical simulations.

Related papers

• Accelerating Error Correction Code Transformers [56.75773430667148]
  We introduce a novel acceleration method for transformer-based decoders. We achieve a 90% compression ratio and reduce arithmetic operation energy consumption by at least 224 times on modern hardware.
  arXiv  Detail & Related papers  (2024-10-08T11:07:55Z)
• Search for Efficient Large Language Models [52.98684997131108]
  Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research. Weight pruning, quantization, and distillation have been embraced to compress LLMs, targeting memory reduction and inference acceleration. Most model compression techniques concentrate on weight optimization, overlooking the exploration of optimal architectures.
  arXiv  Detail & Related papers  (2024-09-25T21:32:12Z)
• Hybrid Dynamic Pruning: A Pathway to Efficient Transformer Inference [1.0919012968294923]
  We introduce a novel algorithm-architecture co-design approach that accelerates transformers using head sparsity, block sparsity and approximation opportunities to reduce computations in attention and reduce memory access. With the observation of the huge redundancy in attention scores and attention heads, we propose a novel integer-based row-balanced block pruning to prune unimportant blocks in the attention matrix at run time. Also propose integer-based head pruning to detect and prune unimportant heads at an early stage at run time.
  arXiv  Detail & Related papers  (2024-07-17T11:15:16Z)
• Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization [0.6445087473595953]
  Large language models (LLMs) demonstrate outstanding performance in various tasks in machine learning. deploying LLM inference poses challenges due to the high compute and memory requirements. We present Tender, an algorithm-hardware co-design solution that enables efficient deployment of LLM inference at low precision.
  arXiv  Detail & Related papers  (2024-06-16T09:51:55Z)
• Lean Attention: Hardware-Aware Scalable Attention Mechanism for the Decode-Phase of Transformers [4.674454841332859]
  Transformer-based models have emerged as one of the most widely used architectures for natural language processing. These huge models are memory hungry and incur significant inference latency even on cutting edge AI-accelerators. We propose LeanAttention, a scalable technique of computing self-attention for the token-generation phase.
  arXiv  Detail & Related papers  (2024-05-17T00:52:39Z)
• Accurate Block Quantization in LLMs with Outliers [0.6138671548064355]
  The demand for inference on extremely large scale LLMs has seen enormous growth in recent months. The problem is aggravated by the exploding raise in the lengths of the sequences being processed. Various quantization techniques have been proposed that allow accurate quantization for both weights and activations.
  arXiv  Detail & Related papers  (2024-03-29T12:15:06Z)
• DeepGEMM: Accelerated Ultra Low-Precision Inference on CPU Architectures using Lookup Tables [49.965024476651706]
  DeepGEMM is a lookup table based approach for the execution of ultra low-precision convolutional neural networks on SIMD hardware. Our implementation outperforms corresponding 8-bit integer kernels by up to 1.74x on x86 platforms.
  arXiv  Detail & Related papers  (2023-04-18T15:13:10Z)
• Energy-efficient Task Adaptation for NLP Edge Inference Leveraging Heterogeneous Memory Architectures [68.91874045918112]
  adapter-ALBERT is an efficient model optimization for maximal data reuse across different tasks. We demonstrate the advantage of mapping the model to a heterogeneous on-chip memory architecture by performing simulations on a validated NLP edge accelerator.
  arXiv  Detail & Related papers  (2023-03-25T14:40:59Z)
• GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training [59.160154997555956]
  We present GradInit, an automated and architecture method for initializing neural networks. It is based on a simple agnostic; the variance of each network layer is adjusted so that a single step of SGD or Adam results in the smallest possible loss value. It also enables training the original Post-LN Transformer for machine translation without learning rate warmup.
  arXiv  Detail & Related papers  (2021-02-16T11:45:35Z)
• Scalable Deep-Learning-Accelerated Topology Optimization for Additively Manufactured Materials [4.221095652322005]
  Topology optimization (TO) is a popular and powerful computational approach for designing novel structures, materials, and devices. To address these issues, we propose a general scalable deep-learning (DL) based TO framework, referred to as SDL-TO. Our framework accelerates TO by learning the iterative history data and simultaneously training on the mapping between the given design and its gradient.
  arXiv  Detail & Related papers  (2020-11-28T17:38:31Z)
• One-step regression and classification with crosspoint resistive memory arrays [62.997667081978825]
  High speed, low energy computing machines are in demand to enable real-time artificial intelligence at the edge. One-step learning is supported by simulations of the prediction of the cost of a house in Boston and the training of a 2-layer neural network for MNIST digit recognition. Results are all obtained in one computational step, thanks to the physical, parallel, and analog computing within the crosspoint array.
  arXiv  Detail & Related papers  (2020-05-05T08:00:07Z)

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.