8-bit Optimizers via Block-wise Quantization

• URL: http://arxiv.org/abs/2110.02861v1
• Date: Wed, 6 Oct 2021 15:43:20 GMT
• Title: 8-bit Optimizers via Block-wise Quantization
• Authors: Tim Dettmers, Mike Lewis, Sam Shleifer, Luke Zettlemoyer
• Abstract summary: Statefuls maintain statistics over time, e.g., the exponentially smoothed sum (SGD with momentum) or squared sum (Adam) of past values. This state can be used to accelerate optimization compared to plain gradient descent but uses memory that might otherwise be allocated to model parameters. In this paper, we develop first gradients that use 8-bit statistics while maintaining the performance levels of using 32-bit gradient states.
• Score: 57.25800395197516
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Stateful optimizers maintain gradient statistics over time, e.g., the exponentially smoothed sum (SGD with momentum) or squared sum (Adam) of past gradient values. This state can be used to accelerate optimization compared to plain stochastic gradient descent but uses memory that might otherwise be allocated to model parameters, thereby limiting the maximum size of models trained in practice. In this paper, we develop the first optimizers that use 8-bit statistics while maintaining the performance levels of using 32-bit optimizer states. To overcome the resulting computational, quantization, and stability challenges, we develop block-wise dynamic quantization. Block-wise quantization divides input tensors into smaller blocks that are independently quantized. Each block is processed in parallel across cores, yielding faster optimization and high precision quantization. To maintain stability and performance, we combine block-wise quantization with two additional changes: (1) dynamic quantization, a form of non-linear optimization that is precise for both large and small magnitude values, and (2) a stable embedding layer to reduce gradient variance that comes from the highly non-uniform distribution of input tokens in language models. As a result, our 8-bit optimizers maintain 32-bit performance with a small fraction of the memory footprint on a range of tasks, including 1.5B parameter language modeling, GLUE finetuning, ImageNet classification, WMT'14 machine translation, MoCo v2 contrastive ImageNet pretraining+finetuning, and RoBERTa pretraining, without changes to the original optimizer hyperparameters. We open-source our 8-bit optimizers as a drop-in replacement that only requires a two-line code change.

Related papers

• COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training [47.07768822212081]
  COAT (States and Activations for FP8 Training) is a novel FP8 training framework designed to significantly reduce memory footprint when training large models. COAT effectively reduces end-to-end training memory footprint by 1.54x compared to BF16. COAT also achieves a 1.43x end-to-end training speedup compared to BF16.
  arXiv  Detail & Related papers  (2024-10-25T05:59:30Z)
• ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models [9.444063879246242]
  We introduce a novel arbitrary-bit quantization algorithm and inference framework, ABQ-LLM. It achieves superior performance across various quantization settings and enables efficient arbitrary-precision quantized inference on the GPU.
  arXiv  Detail & Related papers  (2024-08-16T06:39:08Z)
• Memory Efficient Optimizers with 4-bit States [22.605392665667136]
  We push states bitwidth down to 4-bit through a detailed empirical analysis of first and second moments. We use a smaller block size and propose to utilize both row-wise and column-wise information for better quantization. Our 4-bits are evaluated on a wide variety of benchmarks including natural language understanding, machine translation, image classification, and instruction tuning.
  arXiv  Detail & Related papers  (2023-09-04T10:27:17Z)
• 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)
• Binary and Ternary Natural Language Generation [24.295815261826153]
  Ternary and binary neural networks enable multiplication-free computation. They promise multiple orders of magnitude efficiency gains over full-precision networks. However, such networks have proven very difficult to optimize. We show first ternary and binary transformer models on the downstream tasks of summarization and machine translation.
  arXiv  Detail & Related papers  (2023-06-02T18:01:02Z)
• 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)
• LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale [80.86029795281922]
  We develop a procedure for Int8 matrix multiplication for feed-forward and attention projection layers in transformers. A 175B parameter 16/32-bit checkpoint can be loaded, converted to Int8, and used immediately without performance degradation.
  arXiv  Detail & Related papers  (2022-08-15T17:08:50Z)
• BBTv2: Pure Black-Box Optimization Can Be Comparable to Gradient Descent for Few-Shot Learning [83.26610968655815]
  Black-Box Tuning is a derivative-free approach to optimize continuous prompt tokens prepended to the input of language models. We present BBTv2, a pure black-box optimization approach that can drive language models to achieve comparable results to gradient-based optimization.
  arXiv  Detail & Related papers  (2022-05-23T11:10:19Z)
• Post-Training Sparsity-Aware Quantization [2.2530496464901106]
  Quantization is a technique used in deep neural networks (DNNs) to increase execution performance and hardware efficiency. We propose a sparsity-aware quantization (SPARQ) method, in which the unstructured and dynamic activation sparsity is leveraged in different representation granularities. SPARQ achieves minor accuracy degradation, 2x speedup over widely used hardware architectures, and a practical hardware implementation.
  arXiv  Detail & Related papers  (2021-05-23T20:12:35Z)
• Leveraging Automated Mixed-Low-Precision Quantization for tiny edge microcontrollers [76.30674794049293]
  This paper presents an automated mixed-precision quantization flow based on the HAQ framework but tailored for the memory and computational characteristics of MCU devices. Specifically, a Reinforcement Learning agent searches for the best uniform quantization levels, among 2, 4, 8 bits, of individual weight and activation tensors. Given an MCU-class memory bound to 2MB for weight-only quantization, the compressed models produced by the mixed-precision engine result as accurate as the state-of-the-art solutions.
  arXiv  Detail & Related papers  (2020-08-12T06:09:58Z)

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.