chore: updates

Signed-off-by: Dheeraj Peri <[email protected]>

Author: peri044

docsrc/user_guide/saving_models.rst

@@ -29,14 +29,14 @@ The following code illustrates this approach.
     import torch_tensorrt
 
     model = MyModel().eval().cuda()
-    inputs = torch.randn((1, 3, 224, 224)).cuda()
+    inputs = [torch.randn((1, 3, 224, 224)).cuda()]
     trt_gm = torch_tensorrt.compile(model, ir="dynamo", inputs) # Output is a torch.fx.GraphModule
     trt_script_model = torch.jit.trace(trt_gm, inputs)
     torch.jit.save(trt_script_model, "trt_model.ts")
 
     # Later, you can load it and run inference
     model = torch.jit.load("trt_model.ts").cuda()
-    model(inputs)
+    model(*inputs)
 
 b) ExportedProgram
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -50,15 +50,15 @@ b) ExportedProgram
     import torch_tensorrt
 
     model = MyModel().eval().cuda()
-    inputs = torch.randn((1, 3, 224, 224)).cuda()
+    inputs = [torch.randn((1, 3, 224, 224)).cuda()]
     trt_gm = torch_tensorrt.compile(model, ir="dynamo", inputs) # Output is a torch.fx.GraphModule
     # Transform and create an exported program
     trt_exp_program = torch_tensorrt.dynamo.export(trt_gm, inputs)
     torch.export.save(trt_exp_program, "trt_model.ep")
 
     # Later, you can load it and run inference
     model = torch.export.load("trt_model.ep")
-    model(inputs)
+    model(*inputs)
 
 `torch_tensorrt.dynamo.export` inlines the submodules within a GraphModule to their corresponding nodes and stiches all the nodes together.
 This is needed as `torch._export` serialization cannot handle serializing and deserializing of submodules (`call_module` nodes).
@@ -78,11 +78,11 @@ Torchscript IR
     import torch_tensorrt
 
     model = MyModel().eval().cuda()
-    inputs = torch.randn((1, 3, 224, 224)).cuda()
+    inputs = [torch.randn((1, 3, 224, 224)).cuda()]
     trt_ts = torch_tensorrt.compile(model, ir="ts", inputs) # Output is a ScriptModule object
     torch.jit.save(trt_ts, "trt_model.ts")
 
     # Later, you can load it and run inference
     model = torch.jit.load("trt_model.ts").cuda()
-    model(inputs)
+    model(*inputs)