MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization

• URL: http://arxiv.org/abs/2411.05282v4
• Date: Tue, 29 Apr 2025 18:38:03 GMT
• Title: MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization
• Authors: Akshat Ramachandran, Souvik Kundu, Tushar Krishna,
• Abstract summary: Quantization of foundational models (FMs) is challenging due to the emergence of large magnitude values called outliers.<n>Existing outlier-aware algorithm-architecture co-design techniques either use mixed-precision, retaining outliers at high precision but compromise hardware efficiency, or quantize inliers and outliers at the same precision.<n>We propose MicroScopiQ, a novel co-design technique that leverages pruning to complement outlier-aware quantization.
• Score: 6.456189487006878
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Quantization of foundational models (FMs) is significantly more challenging than traditional DNNs due to the emergence of large magnitude values called outliers. Existing outlier-aware algorithm-architecture co-design techniques either use mixed-precision, retaining outliers at high precision but compromise hardware efficiency, or quantize inliers and outliers at the same precision, improving hardware efficiency at the cost of accuracy. To address this mutual exclusivity, we propose MicroScopiQ, a novel co-design technique that leverages pruning to complement outlier-aware quantization. MicroScopiQ retains outliers at higher precision while pruning a certain fraction of least important weights to distribute the additional outlier bits; ensuring high accuracy, aligned memory and hardware efficiency. We design a high-throughput, low overhead accelerator architecture composed of multi-precision INT processing elements and a network-on-chip called ReCoN that efficiently abstracts the complexity of supporting high-precision outliers. Additionally, unlike prior techniques, MicroScopiQ does not assume any locality of outlier weights, enabling applicability to a broad range of FMs. Extensive experiments across diverse quantization settings demonstrate that MicroScopiQ achieves state-of-the-art quantization accuracy, while delivering up to 3x faster inference and 2x lower energy consumption compared to existing alternatives. Code is available at: https://github.com/georgia-tech-synergy-lab/MicroScopiQ-LLM-Quantization

Related papers

• JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Exploration [38.264287509278866]
  We propose the JAQ Framework, which jointly optimize the three critical dimensions. Memory overhead in software-side: Low-precision quantization-aware training can lead to significant memory usage. Search time-consuming in hardware-side: The discrete nature of hardware parameters and the complex interplay between compiler optimizations and individual operators make the accelerator search time-consuming.
  arXiv  Detail & Related papers  (2025-01-09T16:10:06Z)
• Mixed-precision Neural Networks on RISC-V Cores: ISA extensions for Multi-Pumped Soft SIMD Operations [5.847997723738113]
  Modern embedded microprocessors provide very limited support for mixed-precision NNs. We introduce a hardware-software co-design framework that enables cooperative hardware design, mixed-precision quantization, ISA extensions and inference. Our framework can achieve, on average, 15x energy reduction for less than 1% accuracy loss and outperforms the ISA-agnostic state-of-the-art RISC-V cores.
  arXiv  Detail & Related papers  (2024-07-19T12:54:04Z)
• OutlierTune: Efficient Channel-Wise Quantization for Large Language Models [24.645237670811476]
  OutlierTune is an efficient per-channel post-training quantization method for the activations of large language models. The proposed framework is easy to implement and hardware-efficient, introducing almost no additional computational overheads during the inference.
  arXiv  Detail & Related papers  (2024-06-27T02:02:26Z)
• 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)
• SySMOL: Co-designing Algorithms and Hardware for Neural Networks with Heterogeneous Precisions [20.241671088121144]
  Recent quantization techniques have enabled heterogeneous precisions at very fine granularity. These networks require additional hardware to decode the precision settings for individual variables, align the variables, and provide fine-grained mixed-precision compute capabilities. We present an end-to-end co-design approach to efficiently execute networks with fine-grained heterogeneous precisions.
  arXiv  Detail & Related papers  (2023-11-23T17:20:09Z)
• 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)
• 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)
• 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)
• Faster Attention Is What You Need: A Fast Self-Attention Neural Network Backbone Architecture for the Edge via Double-Condensing Attention Condensers [71.40595908386477]
  We introduce a new faster attention condenser design called double-condensing attention condensers. The resulting backbone (which we name AttendNeXt) achieves significantly higher inference throughput on an embedded ARM processor. These promising results demonstrate that exploring different efficient architecture designs and self-attention mechanisms can lead to interesting new building blocks for TinyML applications.
  arXiv  Detail & Related papers  (2022-08-15T02:47:33Z)
• 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)
• 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)
• Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search [112.05977301976613]
  We propose to combine Network Architecture Search methods with quantization to enjoy the merits of the two sides. We first propose the joint training of architecture and quantization with a shared step size to acquire a large number of quantized models. Then a bit-inheritance scheme is introduced to transfer the quantized models to the lower bit, which further reduces the time cost and improves the quantization accuracy.
  arXiv  Detail & Related papers  (2020-10-09T03:52:16Z)

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.