mlsanityData to 14 Oct 2026

An Empirical Study of openPangu Quantization on Ascend NPUs

arXiv 2606.21257 ↗First posted 19 Jun 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

openPangu models are attractive targets for private and domestic large-language-model deployment, yet their robustness under aggressive post-training quantization on Ascend NPUs has not been systematically characterized. This paper conducts a controlled empirical study of openPangu 1B and 7B models on Huawei Ascend 910B1 NPUs. We evaluate representative weight-only and weight-activation post-training quantization methods, including RTN, GPTQ, AWQ, SmoothQuant, GPTAQ, BiLLM, and SliM-LLM, under a unified calibration and evaluation protocol. Across 18 evaluation tasks, we find that 8-bit weight-only quantization is effectively lossless for both models, while 4-bit quantization remains practical for the 7B model but is visibly more harmful for the 1B model on reasoning, math, and code tasks. Ultra-low precision remains challenging: most 2-bit and binary settings collapse to near-random behavior, and W4A4 SmoothQuant produces non-finite perplexity in our evaluation. These results provide an NPU-oriented accuracy map for selecting openPangu quantization settings and highlight the persistent difficulty of extreme low-bit compression.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 18 references that are in the map. First posted on arXiv 19 Jun 2026.

Builds on

17 of 18 references.

References · 17

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  4. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  5. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  6. 2016Pointer Sentinel Mixture Modelscited by 3,096
  7. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,883
  8. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,183
  9. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  10. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
  11. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
  12. 2024SpinQuant: LLM quantization with learned rotationscited by 471
5 more
  1. 2024BiLLM: Pushing the Limit of Post-Training Quantization for LLMscited by 144
  2. 2023RPTQ: Reorder-based Post-training Quantization for Large Language Modelscited by 116
  3. 2024SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Modelscited by 63
  4. 2025GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibrationcited by 60
  5. 2024A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithmscited by 31

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Post-Training Quantization of OpenPangu Models for Efficient Deployment on Atlas A2
  2. 2026Quant.npu: Enabling Efficient Mobile NPU Inference for on-device LLMs via Fully Static Quantization
  3. 2024Optimizing Large Language Models through Quantization: A Comparative Analysis of PTQ and QAT Techniques
  4. 2026A Case Study of Selected PTQ Baselines for Reasoning LLMs on Ascend NPU
  5. 2025NeUQI: Near-Optimal Uniform Quantization Parameter Initialization for Low-Bit LLMs
  6. 2024MobileQuant: Mobile-friendly Quantization for On-device Language Models
  7. 2023Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantization
  8. 2023Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge