# Post-Training Quantization of OpenPangu Models for Efficient Deployment on Atlas A2

arXiv: https://arxiv.org/abs/2512.23367 · HTML: https://mlsanity.com/paper/2512.23367/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 32 references that are in the map.
- First posted on arXiv 29 Dec 2025.

## Builds on (most cited first, 27 of 27)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers](https://mlsanity.com/paper/2206.01861/) (2022)
- [A White Paper on Neural Network Quantization](https://mlsanity.com/paper/2106.08295/) (2021)
- [SpinQuant: LLM quantization with learned rotations](https://mlsanity.com/paper/2405.16406/) (2024)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (2018)
- [OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models](https://mlsanity.com/paper/2308.13137/) (2023)
- [QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving](https://mlsanity.com/paper/2405.04532/) (2024)
- [DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs](https://mlsanity.com/paper/2406.01721/) (2024)
- [Understanding and Overcoming the Challenges of Efficient Transformer Quantization](https://mlsanity.com/paper/2109.12948/) (2021)
- [OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models](https://mlsanity.com/paper/2306.02272/) (2023)
- [A Review on Edge Large Language Models: Design, Execution, and Applications](https://mlsanity.com/paper/2410.11845/) (2024)
- [ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation](https://mlsanity.com/paper/2303.08302/) (2023)
- [Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models](https://mlsanity.com/paper/2504.04823/) (2025)
- [Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition](https://mlsanity.com/paper/2505.22375/) (2025)
- [A Comprehensive Evaluation of Quantization Strategies for Large Language Models](https://mlsanity.com/paper/2402.16775/) (2024)
- [Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoning](https://mlsanity.com/paper/2501.03035/) (2025)
- [Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantization](https://mlsanity.com/paper/2311.05161/) (2023)
- [MicroMix: Efficient Mixed-Precision Quantization with Microscaling Formats for Large Language Models](https://mlsanity.com/paper/2508.02343/) (2025)
- [Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques](https://mlsanity.com/paper/2505.02309/) (2025)
- [CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression](https://mlsanity.com/paper/2410.07505/) (2024)

## Built on by (most cited first, 1 of 1)

- [Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning](https://mlsanity.com/paper/2602.07605/) (2026)

## Abstract (arXiv)

Huawei's openPangu-Embedded-1B and openPangu-Embedded-7B are variants of the openPangu large language model, designed for efficient deployment on Ascend NPUs. The 7B variant supports three distinct Chain-of-Thought (CoT) reasoning paradigms, namely slowthink, autothink, and nothink, while the 1B variant operates exclusively in the nothink mode, which employs condensed reasoning for higher efficiency. Although CoT reasoning enhances capability, the generation of extended reasoning traces introduces substantial memory and latency overheads, posing challenges for practical deployment on Ascend NPUs. This paper addresses these computational constraints by leveraging low-bit quantization, which transforms FP16 computations into more efficient integer arithmetic. We introduce a unified low-bit inference framework, supporting INT8 (W8A8) and W4A8 quantization, specifically optimized for openPangu-Embedded models on the Atlas A2. Our comprehensive evaluation on code generation benchmarks (HumanEval and MBPP) demonstrates the efficacy of this approach. INT8 quantization consistently preserves over 90% of the FP16 baseline accuracy and achieves a 1.5x prefill speedup on the Atlas A2. Furthermore, W4A8 quantization significantly reduces memory consumption, albeit with a moderate trade-off in accuracy. These findings collectively indicate that low-bit quantization effectively facilitates efficient CoT reasoning on Ascend NPUs, maintaining high model fidelity.