Quantization

英文原文文件：quantization.md

计算解释

通过降低数值精度来缓解内存、带宽与延迟压力的部署技术。

支撑阅读卡

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (2017, efficient_edge_inference)
• GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers (2022, efficient_edge_inference)
• QLoRA: Efficient Finetuning of Quantized LLMs (2023, efficient_edge_inference)
• Gemma 3 Technical Report (2025, efficient_edge_inference)
• BitNet b1.58 2B4T Technical Report (2025, efficient_edge_inference)

后续计算范式下过时或退居次要的内容

仅通过已链接的阅读卡追踪，不将本方法页视为独立证据来源。