SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression

• URL: http://arxiv.org/abs/2410.09615v2
• Date: Tue, 04 Feb 2025 01:30:52 GMT
• Title: SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression
• Authors: Mohammad Mozaffari, Amir Yazdanbakhsh, Maryam Mehri Dehnavi,
• Abstract summary: SLIM is a new one-shot compression framework that holistically integrates hardware-friendly quantization, sparsity, and low-rank approximation. SLIM improves model accuracy by up to 5.66% (LLaMA-2-7B) for 2:4 sparsity with 4-bit weight quantization, outperforming prior methods. We also propose an optional PEFT recipe that further improves accuracy by up to 1.66% (LLaMA-2-13B) compared to SLIM without fine-tuning.
• Score: 7.6131620435684875
• License:
• Abstract: Conventional model compression techniques for LLMs address high memory consumption and slow inference challenges but typically require computationally expensive retraining to preserve accuracy. In contrast, one-shot compression methods eliminate retraining cost, but struggle to achieve accuracy comparable to dense models. This paper presents SLIM, a new one-shot compression framework that holistically integrates hardware-friendly quantization, sparsity, and low-rank approximation into a unified process. First, we formulate the quantization process using a probabilistic approach (SLIM-Quant) that enables us to apply uniform quantization. Then, we use an existing one-shot pruning method to apply semi-structured sparsity on top of the quantized weights. Finally, to compensate for the introduced aggregated quantization and sparsity error, we use a novel saliency function with unique invertible and additive features that enables us to mathematically compute the value of low-rank adapters. SLIM improves model accuracy by up to 5.66% (LLaMA-2-7B) for 2:4 sparsity with 4-bit weight quantization, outperforming prior methods. Models compressed with SLIM achieve up to 3.78x and 3.75x layer-wise speedup on Nvidia RTX3060 and A100 GPUs, respectively. We also propose an optional PEFT recipe that further improves accuracy by up to 1.66% (LLaMA-2-13B) compared to SLIM without fine-tuning

Related papers

• SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models [58.5019443418822]
  Diffusion models have been proven highly effective at generating high-quality images. As these models grow larger, they require significantly more memory and suffer from higher latency. In this work, we aim to accelerate diffusion models by quantizing their weights and activations to 4 bits.
  arXiv  Detail & Related papers  (2024-11-07T18:59:58Z)
• 2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution [83.09117439860607]
  Low-bit quantization has become widespread for compressing image super-resolution (SR) models for edge deployment. It is notorious that low-bit quantization degrades the accuracy of SR models compared to their full-precision (FP) counterparts. We present a dual-stage low-bit post-training quantization (PTQ) method for image super-resolution, namely 2DQuant, which achieves efficient and accurate SR under low-bit quantization.
  arXiv  Detail & Related papers  (2024-06-10T06:06:11Z)
• SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models [67.67135738642547]
  Post-training quantization (PTQ) is a powerful compression technique investigated in large language models (LLMs) Existing PTQ methods are not ideal in terms of accuracy and efficiency, especially with below 4 bit-widths. This paper presents a Salience-Driven Mixed-Precision Quantization scheme for LLMs, namely SliM-LLM.
  arXiv  Detail & Related papers  (2024-05-23T16:21:48Z)
• Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization [14.201092042777299]
  Large language models (LLMs) have demonstrated impressive abilities in various domains while the inference cost is expensive. Applying 2-bit single-precision weight quantization brings >3% accuracy loss. We propose mixed-precision quantization for each weight matrix and asynchronous dequantization during inference.
  arXiv  Detail & Related papers  (2023-11-28T02:44:59Z)
• SqueezeLLM: Dense-and-Sparse Quantization [80.32162537942138]
  Main bottleneck for generative inference with LLMs is memory bandwidth, rather than compute, for single batch inference. We introduce SqueezeLLM, a post-training quantization framework that enables lossless compression to ultra-low precisions of up to 3-bit. Our framework incorporates two novel ideas: (i) sensitivity-based non-uniform quantization, which searches for the optimal bit precision assignment based on second-order information; and (ii) the Dense-and-Sparse decomposition that stores outliers and sensitive weight values in an efficient sparse format.
  arXiv  Detail & Related papers  (2023-06-13T08:57:54Z)
• SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression [76.73007709690306]
  We introduce the Sparse-Quantized Representation (SpQR), a new compressed format and quantization technique. SpQR achieves relative accuracy losses of less than 1% in perplexity for highly-accurate LLaMA and Falcon LLMs. This makes it possible to run 33B parameter LLM on a single 24 GB consumer GPU without any performance degradation at 15% speedup.
  arXiv  Detail & Related papers  (2023-06-05T17:53:28Z)
• Pruning Ternary Quantization [32.32812780843498]
  Inference time, model size, and accuracy are three key factors in deep model compression. We propose pruning ternary quantization (PTQ): a simple, effective, symmetric ternary quantization method. Our method is verified on image classification, object detection/segmentation tasks with different network structures.
  arXiv  Detail & Related papers  (2021-07-23T02:18:00Z)
• Learnable Companding Quantization for Accurate Low-bit Neural Networks [3.655021726150368]
  Quantizing deep neural networks is an effective method for reducing memory consumption and improving inference speed. It is still hard for extremely low-bit models to achieve accuracy comparable with that of full-precision models. We propose learnable companding quantization (LCQ) as a novel non-uniform quantization method for 2-, 3-, and 4-bit models.
  arXiv  Detail & Related papers  (2021-03-12T09:06:52Z)
• Training with Quantization Noise for Extreme Model Compression [57.51832088938618]
  We tackle the problem of producing compact models, maximizing their accuracy for a given model size. A standard solution is to train networks with Quantization Aware Training, where the weights are quantized during training and the gradients approximated with the Straight-Through Estimator. In this paper, we extend this approach to work beyond int8 fixed-point quantization with extreme compression methods.
  arXiv  Detail & Related papers  (2020-04-15T20:10:53Z)

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.