Apply dynamic quantization
You've successfully trained a neural network model for deployment, and now you want to optimize it using dynamic quantization. This step is crucial for deploying your model efficiently in environments with limited resources.
The model has been pre-loaded.
Den här övningen är en del av kursen
Scalable AI Models with PyTorch Lightning
Övningsinstruktioner
- Import the necessary quantization module from PyTorch.
- Apply dynamic quantization targeting linear layers, using 8-bit integer precision.
Interaktiv övning med praktiskt arbete
Testa den här övningen genom att slutföra den här exempelkoden.
import torch
# Import the necessary quantization module
from torch.quantization import ____
# Apply dynamic quantization targeting linear layers
model_quantized = torch.quantization.____(
____, {torch.nn.____}, dtype=torch.____
)