Computational Graph is extracted using LibTorch, so it's not as fast as torch.compile(). However, it's simpler to use and offers better compatibility.
- Speed Optimization with Graph Optimization
- Easier Deployment without python
- Debugging and Analysis with Computational Graph Visualization
import torch import torch.nn as nn class Model(nn.Module): def __init__(self): super().__init__() self.fc = nn.Linear(10, 1) def forward(self, x): return self.fc(x) model = Model() scripted_model = torch.jit.script(model) scripted_model.save("model.pt")
torch.jit members