Model Compression
Quantization
https://github.com/666DZY666/micronet
GitHub - TimDettmers/bitsandbytes: 8-bit CUDA functions for PyTorch
Knowledge Distillation
For Knowledge Distillation see this note
https://github.com/666DZY666/micronet
GitHub - TimDettmers/bitsandbytes: 8-bit CUDA functions for PyTorch
For Knowledge Distillation see this note