Fusions · Quantization · Compilation

Deploy PyTorch models
on edge hardware.

Hardware-aware graph transforms, fusions, and optimal quantization
in PyTorch.

Click a card to compare a model with the deployment-ready model for TensorRT

ResNet-50 CNN
25M params · 50 layers · 497 nodes
Original + Embedl Deploy (55 fusions)
ViT-B/16 Transformer
86M params · 12 heads · 280 nodes
Original + Embedl Deploy (87 fusions)
ConvNext Tiny ConvNet
28M params · 4 stages · 340 nodes
Original + Embedl Deploy (78 fusions)
or try your own model

Drop your .pt2 file here

or