AMD FidelityFX Super Resolution FP32 fallback tested, native FP16 is 7% faster - VideoCardz.com
Automatic Mixed Precision Training-Document-PaddlePaddle Deep Learning Platform
Automatic Mixed Precision (AMP) Training
philschmid/gpt-j-6B-fp16-sharded · Hugging Face
Arm NN for GPU inference FP16 and FastMath - AI and ML blog - Arm Community blogs - Arm Community
Pytorch自动混合精度(AMP)介绍与使用- jimchen1218 - 博客园
FP16, VS INT8 VS INT4? - Folding Forum
Mixed-Precision Training of Deep Neural Networks | NVIDIA Technical Blog
Understanding Mixed Precision Training | by Jonathan Davis | Towards Data Science
What is the TensorFloat-32 Precision Format? | NVIDIA Blog
fastai - Mixed precision training
MindSpore
![RFC][Relay] FP32 -> FP16 Model Support - pre-RFC - Apache TVM Discuss](https://discuss.tvm.apache.org/uploads/default/original/2X/4/450bd810eb5b388a3dc4864b1bdd5f78cd01d2dc.png "RFC][Relay] FP32 -> FP16 Model Support - pre-RFC - Apache TVM Discuss")
RFC][Relay] FP32 -> FP16 Model Support - pre-RFC - Apache TVM Discuss
A Shallow Dive Into Tensor Cores - The NVIDIA Titan V Deep Learning Deep Dive: It's All About The Tensor Cores
Bfloat16 – a brief intro - AEWIN
fp16 – Nick Higham
Using Tensor Cores for Mixed-Precision Scientific Computing | NVIDIA Technical Blog
