mlsanityData to 14 Oct 2026

APSQ: Additive Partial Sum Quantization with Algorithm-Hardware Co-Design

arXiv 2505.03748 ↗First posted 10 Apr 2025cs.AR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

DNN accelerators, significantly advanced by model compression and specialized dataflow techniques, have marked considerable progress. However, the frequent access of high-precision partial sums (PSUMs) leads to excessive memory demands in architectures utilizing input/weight stationary dataflows. Traditional compression strategies have typically overlooked PSUM quantization, which may account for 69% of power consumption. This study introduces a novel Additive Partial Sum Quantization (APSQ) method, seamlessly integrating PSUM accumulation into the quantization framework. A grouping strategy that combines APSQ with PSUM quantization enhanced by a reconfigurable architecture is further proposed. The APSQ performs nearly lossless on NLP and CV tasks across BERT, Segformer, and EfficientViT models while compressing PSUMs to INT8. This leads to a notable reduction in energy costs by 28-87%. Extended experiments on LLaMA2-7B demonstrate the potential of APSQ for large language models. Code is available at https://github.com/Yonghao-Tan/APSQ.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 29 references that are in the map. First posted on arXiv 10 Apr 2025.

Builds on

17 of 29 references.

References · 17

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  6. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  7. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  8. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  9. 2019Learned Step Size Quantizationcited by 628
  10. 2021I-BERT: Integer-only BERT Quantizationcited by 255
  11. 2019MetaPruning: Meta Learning for Automatic Neural Network Channel Pruningcited by 227
  12. 2020Channel-wise Knowledge Distillation for Dense Predictioncited by 163
5 more
  1. 2023Oscillation-free Quantization for Low-bit Vision Transformerscited by 57
  2. 2022ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Designcited by 41
  3. 2022Centralized Feature Pyramid for Object Detectioncited by 13
  4. 2024RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantizationcited by 13
  5. 2024Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformerscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models
  2. 2025PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models
  3. 2024ApiQ: Finetuning of 2-Bit Quantized Large Language Model
  4. 2026SEPTQ: A Simple and Effective Post-Training Quantization Paradigm for Large Language Models
  5. 2025Unifying Block-wise PTQ and Distillation-based QAT for Progressive Quantization toward 2-bit Instruction-Tuned LLMs
  6. 2026D2Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs
  7. 2024Evaluating Quantized Large Language Models
  8. 2025PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models