mlsanityData to 14 Oct 2026

Arithmetic-Intensity-Aware Quantization

arXiv 2512.14090 ↗First posted 16 Dec 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

As modern neural networks become increasingly memory-bound, inference throughput is limited by DRAM bandwidth rather than compute. We present Arithmetic-Intensity-Aware Quantization (AIQ), a mixed precision quantization framework that chooses per-layer bit-widths to maximize arithmetic intensity (AI) while minimizing accuracy loss. AIQ is a post-training quantization method that uses search algorithms over per-layer quantization schemes to minimize a weighted loss over AI and accuracy. On ResNet-20/CIFAR-10, AIQ increases AI by ~50% over an FP32 baseline while keeping test accuracy within ~1 percentage point, and outperforming global uniform quantization schemes. On a memory-bound MobileNetV2 architecture, AIQ configurations give a 1.66x higher throughput than the FP32 baseline while keeping test accuracy within 1 percentage point. We also find that AIQ naturally quantizes larger layers more aggressively.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 17 references that are in the map. First posted on arXiv 16 Dec 2025.

Builds on

13 of 17 references.

References · 13

  1. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  2. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
  3. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 569
  4. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 443
  5. 2019HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precisioncited by 402
  6. 2023Atom: Low-bit Quantization for Efficient and Accurate LLM Servingcited by 272
  7. 2023A Survey on Model Compression for Large Language Modelscited by 269
  8. 2024LLM Inference Unveiled: Survey and Roofline Model Insightscited by 152
  9. 2024A Survey on Transformer Compressioncited by 46
  10. 2022Post-training Quantization for Neural Networks with Provable Guaranteescited by 33
  11. 2023Efficient Post-training Quantization with FP8 Formatscited by 29
  12. 2024INT-FlashAttention: Enabling Flash Attention for INT8 Quantizationcited by 9
1 more
  1. 2023SimQ-NAS: Simultaneous Quantization Policy and Neural Architecture Searchcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Dual Precision Quantization for Efficient and Accurate Deep Neural Networks Inference
  2. 2021A White Paper on Neural Network Quantization
  3. 2024A2Q+: Improving Accumulator-Aware Weight Quantization
  4. 2023On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks
  5. 2025InfoQ: Mixed-Precision Quantization via Global Information Flow
  6. 2022F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization
  7. 2023A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidance
  8. 2021VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference