A White Paper on Neural Network Deployment
Ctrlk
  • ❤️‍🔥A White Paper on Neural Network Deployment
    • ❤️‍🔥A White Paper on Neural Network Deployment
    • 🤠CUDA
    • 😄ONNX
    • 🐶TensorRT
    • 🫶模型量化和剪枝
      • 🖕IEEE754标准
      • 🫰浮点运算产生的误差
      • 🤲映射和偏移
      • 🫴quantization from scratch|python
      • 👏动态量化范围
      • 🤝量化粒度
      • 👍校准
      • 👊Post-Training Quantization
      • ✊Quantization-Aware Training
      • 🤞pytorch-quantization使用文档
      • ✌️Polygraphy-Cheatsheet
    • 🤺杂文不杂
    • 🍀CPP
    • 🩷部署实战
    • ☯️重点参考书籍
Powered by GitBook
On this page

Was this helpful?

Edit
  1. ❤️‍🔥A White Paper on Neural Network Deployment

🫶模型量化和剪枝

🖕IEEE754标准🫰浮点运算产生的误差🤲映射和偏移🫴quantization from scratch|python👏动态量化范围🤝量化粒度👍校准👊Post-Training Quantization✊Quantization-Aware Training🤞pytorch-quantization使用文档✌️Polygraphy-Cheatsheet
Previous手撕TensoRT源码|0x00NextIEEE754标准

Was this helpful?