C++ deployment

Author: laikhtewari

README.md

@@ -62,7 +62,8 @@ model = MyModel().eval().cuda() # define your model here
 inputs = [torch.randn((1, 3, 224, 224)).cuda()] # define a list of relevant inputs here
 
 trt_gm = torch_tensorrt.compile(model, ir="dynamo", inputs) 
-torchtrt.save(trt_gm, "trt.ep", inputs=inputs)
+torch_tensorrt.save(trt_gm, "trt.ep", inputs=inputs) # PyTorch only supports Python runtime for an ExportedProgram. For C++ deployment, use a TorchScript file
+torch_tensorrt.save(trt_gm, "trt.ts", output_format="torchscript", inputs=inputs)
 ```
 
 #### Step 2: Deploy
@@ -84,7 +85,9 @@ model(*inputs)
 #include "torch/script.h"
 #include "torch_tensorrt/torch_tensorrt.h"
 
-// to fill
+auto trt_mod = torch::jit::load("trt.ts");
+auto input_tensor = [...]; // fill this with your inputs
+auto results = trt_mod.forward({input_tensor});
 ```
 
 ## Further resources