371 B
371 B
https://arxiv.org/pdf/2209.05433
FP8 FORMATS FOR DEEP LEARNING
FP8 Quantization: The Power of the Exponent
https://arxiv.org/pdf/2208.09225
https://zhuanlan.zhihu.com/p/574825662
FP8 量化-原理、实现与误差分析
https://zhuanlan.zhihu.com/p/619431625
FP8 量化基础
https://developer.nvidia.com/zh-cn/blog/nvidia-gpu-fp8-training-inference/