MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design

• URL: http://arxiv.org/abs/2412.14590v1
• Date: Thu, 19 Dec 2024 07:15:15 GMT
• Title: MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design
• Authors: Zhen Zheng, Xiaonan Song, Chuanjie Liu,
• Abstract summary: We make a comprehensive analysis of the general quantization principles on their effect to the triangle of accuracy, memory consumption and system efficiency. We propose MixLLM that explores the new optimization space of mixed-precision quantization between output features. We present the sweet spot of quantization configuration of algorithm-system co-design that leads to high accuracy and system efficiency.
• Score: 1.3589914205911104
• License:
• Abstract: Quantization has become one of the most effective methodologies to compress LLMs into smaller size. However, the existing quantization solutions still show limitations of either non-negligible accuracy drop or system inefficiency. In this paper, we make a comprehensive analysis of the general quantization principles on their effect to the triangle of accuracy, memory consumption and system efficiency. We propose MixLLM that explores the new optimization space of mixed-precision quantization between output features based on the insight that different output features matter differently in the model. MixLLM identifies the output features with high salience in the global view rather than within each single layer, effectively assigning the larger bit-width to output features that need it most to achieve good accuracy with low memory consumption. We present the sweet spot of quantization configuration of algorithm-system co-design that leads to high accuracy and system efficiency. To address the system challenge, we design the two-step dequantization to make use of the int8 Tensor Core easily and fast data type conversion to reduce dequantization overhead significantly, and present the software pipeline to overlap the memory access, dequantization and the MatMul to the best. Extensive experiments show that with only 10% more bits, the PPL increasement can be reduced from about 0.5 in SOTA to within 0.2 for Llama 3.1 70B, while on average MMLU-Pro improves by 0.93 over the SOTA of three popular models. In addition to its superior accuracy, MixLLM also achieves state-of-the-art system efficiency.

Related papers

• MixPE: Quantization and Hardware Co-design for Efficient LLM Inference [16.42907854119748]
  MixPE is a specialized mixed-precision processing element designed for efficient low-bit quantization in large language models. We show that MixPE surpasses the state-of-the-art quantization accelerators by $2.6times$ speedup and $1.4times$ energy reduction.
  arXiv  Detail & Related papers  (2024-11-25T07:34:53Z)
• 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)
• LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit [55.73370804397226]
  Quantization, a key compression technique, can effectively mitigate these demands by compressing and accelerating large language models. We present LLMC, a plug-and-play compression toolkit, to fairly and systematically explore the impact of quantization. Powered by this versatile toolkit, our benchmark covers three key aspects: calibration data, algorithms (three strategies), and data formats.
  arXiv  Detail & Related papers  (2024-05-09T11:49:05Z)
• On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks [52.97107229149988]
  We propose an On-Chip Hardware-Aware Quantization framework, performing hardware-aware mixed-precision quantization on deployed edge devices. For efficiency metrics, we built an On-Chip Quantization Aware pipeline, which allows the quantization process to perceive the actual hardware efficiency of the quantization operator. For accuracy metrics, we propose Mask-Guided Quantization Estimation technology to effectively estimate the accuracy impact of operators in the on-chip scenario.
  arXiv  Detail & Related papers  (2023-09-05T04:39:34Z)
• FineQuant: Unlocking Efficiency with Fine-Grained Weight-Only Quantization for LLMs [9.072821427818557]
  Large Language Models (LLMs) have achieved state-of-the-art performance across various language tasks but pose challenges for practical deployment. We propose an efficient weight-only quantization method that reduces memory consumption and accelerates inference for LLMs. We evaluate our approach on large-scale open source models such as OPT-175B and internal MoE models, showcasing minimal accuracy loss while achieving up to 3.65 times higher throughput.
  arXiv  Detail & Related papers  (2023-08-16T23:57:41Z)
• 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)
• AMED: Automatic Mixed-Precision Quantization for Edge Devices [3.5223695602582614]
  Quantized neural networks are well known for reducing the latency, power consumption, and model size without significant harm to the performance. Mixed-precision quantization offers better utilization of customized hardware that supports arithmetic operations at different bitwidths.
  arXiv  Detail & Related papers  (2022-05-30T21:23:22Z)
• Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition [67.95996816744251]
  State-of-the-art language models (LMs) represented by long-short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming increasingly complex and expensive for practical applications. Current quantization methods are based on uniform precision and fail to account for the varying performance sensitivity at different parts of LMs to quantization errors. Novel mixed precision neural network LM quantization methods are proposed in this paper.
  arXiv  Detail & Related papers  (2021-11-29T12:24:02Z)
• Fully Quantized Image Super-Resolution Networks [81.75002888152159]
  We propose a Fully Quantized image Super-Resolution framework (FQSR) to jointly optimize efficiency and accuracy. We apply our quantization scheme on multiple mainstream super-resolution architectures, including SRResNet, SRGAN and EDSR. Our FQSR using low bits quantization can achieve on par performance compared with the full-precision counterparts on five benchmark datasets.
  arXiv  Detail & Related papers  (2020-11-29T03:53:49Z)
• Layer-specific Optimization for Mixed Data Flow with Mixed Precision in FPGA Design for CNN-based Object Detectors [16.56630393243829]
  Convolutional neural networks (CNNs) require both intensive computation and frequent memory access. This paper proposes a layer-specific design that employs different organizations that are optimized for the different layers. The proposed design employs two layer-specific optimizations: layer-specific mixed data flow and layer-specific mixed precision.
  arXiv  Detail & Related papers  (2020-09-03T11:27:40Z)

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.