Fix dead links in cpp docs

cpp/README.md

@@ -34,30 +34,30 @@ cd serve
 torchserve torchserve --ncs --start --model-store model_store
 ```
 ## Backend
-TorchServe cpp backend can run as a process, which is similar to [TorchServe Python backend](https://github.com/pytorch/serve/tree/master/ts). By default, TorchServe supports torch scripted model in cpp backend. Other platforms such as MxNet, ONNX can be supported through custom handlers following the TorchScript example [src/backends/handler/torch_scripted_handler.hh](https://github.com/pytorch/serve/blob/master/src/backends/handler/torch_scripted_handler.hh).
+TorchServe cpp backend can run as a process, which is similar to [TorchServe Python backend](https://github.com/pytorch/serve/tree/master/ts). By default, TorchServe supports torch scripted model in cpp backend. Other platforms such as MxNet, ONNX can be supported through custom handlers following the TorchScript example [src/backends/handler/torch_scripted_handler.hh](https://github.com/pytorch/serve/blob/master/cpp/src/backends/handler/torch_scripted_handler.hh).
 ### Custom Handler
-By default, TorchServe cpp provides a handler for TorchScript [src/backends/handler/torch_scripted_handler.hh](https://github.com/pytorch/serve/blob/master/src/backends/handler/torch_scripted_handler.hh). Its uses the [BaseHandler](https://github.com/pytorch/serve/blob/master/src/backends/handler/base_handler.hh) which defines the APIs to customize handler.
-* [Initialize](serve/blob/cpp_backend/cpp/src/backends/handler/base_handler.hh#L29)
-* [LoadModel](serve/blob/cpp_backend/cpp/src/backends/handler/base_handler.hh#L37)
-* [Preprocess](serve/blob/cpp_backend/cpp/src/backends/handler/base_handler.hh#L40)
-* [Inference](serve/blob/cpp_backend/cpp/src/backends/handler/base_handler.hh#L46)
-* [Postprocess](serve/blob/cpp_backend/cpp/src/backends/handler/base_handler.hh#L53)
+By default, TorchServe cpp provides a handler for TorchScript [src/backends/handler/torch_scripted_handler.hh](https://github.com/pytorch/serve/blob/master/cpp/src/backends/handler/torch_scripted_handler.hh). Its uses the [BaseHandler](https://github.com/pytorch/serve/blob/master/cpp/src/backends/handler/base_handler.hh) which defines the APIs to customize handler.
+* [Initialize](https://github.com/pytorch/serve/blob/ba8f96a6e68ca7f63b55d72a21aad364334e4d8e/cpp/src/backends/handler/base_handler.hh#L34)
+* [LoadModel](https://github.com/pytorch/serve/blob/ba8f96a6e68ca7f63b55d72a21aad364334e4d8e/cpp/src/backends/handler/base_handler.hh#L41)
+* [Preprocess](https://github.com/pytorch/serve/blob/ba8f96a6e68ca7f63b55d72a21aad364334e4d8e/cpp/src/backends/handler/base_handler.hh#L43)
+* [Inference](https://github.com/pytorch/serve/blob/ba8f96a6e68ca7f63b55d72a21aad364334e4d8e/cpp/src/backends/handler/base_handler.hh#L49)
+* [Postprocess](https://github.com/pytorch/serve/blob/ba8f96a6e68ca7f63b55d72a21aad364334e4d8e/cpp/src/backends/handler/base_handler.hh#L55)
 #### Usage
 ##### Using TorchScriptHandler
 * set runtime as "LSP" in model archiver option [--runtime](https://github.com/pytorch/serve/tree/master/model-archiver#arguments)
 * set handler as "TorchScriptHandler" in model archiver option [--handler](https://github.com/pytorch/serve/tree/master/model-archiver#arguments)
 ```
  torch-model-archiver --model-name mnist_base --version 1.0 --serialized-file mnist_script.pt --handler TorchScriptHandler --runtime LSP
 ```
-Here is an [example](https://github.com/pytorch/serve/tree/cpp_backend/cpp/test/resources/examples/mnist/base_handler) of unzipped model mar file.
+Here is an [example](https://github.com/pytorch/serve/tree/master/cpp/test/resources/examples/mnist/base_handler) of unzipped model mar file.
 ##### Using Custom Handler
 * build customized handler shared lib. For example [Mnist handler](https://github.com/pytorch/serve/blob/cpp_backend/cpp/src/examples/image_classifier/mnist).
 * set runtime as "LSP" in model archiver option [--runtime](https://github.com/pytorch/serve/tree/master/model-archiver#arguments)
 * set handler as "libmnist_handler:MnistHandler" in model archiver option [--handler](https://github.com/pytorch/serve/tree/master/model-archiver#arguments)
 ```
 torch-model-archiver --model-name mnist_handler --version 1.0 --serialized-file mnist_script.pt --handler libmnist_handler:MnistHandler --runtime LSP
 ```
-Here is an [example](https://github.com/pytorch/serve/tree/cpp_backend/cpp/test/resources/examples/mnist/mnist_handler) of unzipped model mar file.
+Here is an [example](https://github.com/pytorch/serve/tree/master/cpp/test/resources/examples/mnist/mnist_handler) of unzipped model mar file.
 
 #### Examples
 We have created a couple of examples that can get you started with the C++ backend.

examples/cpp/aot_inductor/llama2/README.md

@@ -20,7 +20,7 @@ We will need the handler .so file as well as the stories15M.so file containing t
 cd ~/serve/examples/cpp/aot_inductor/llama2
 cp ../../../../cpp/_build/test/resources/examples/aot_inductor/llama_handler/libllama_so_handler.so ./
 ```
-We will leave the model .so file in place and just use its [path](../../../../cpp/_build/test/resources/examples/aot_inductor/llama_handler/stories15M.so) in the next step.
+We will leave the model .so file in place and just use its absolute path in the next step.
 
 4. Create a [config.json](config.json) with the path of the downloaded model and tokenizer:
 

examples/cpp/babyllama/README.md

@@ -1,6 +1,6 @@
 ## BabyLlama example
 
-This example is adapted from https://github.com/karpathy/llama2.c. The handler C++ source code for this examples can be found [here](../../../cpp/src/examples/babyllama/).
+This example is adapted from https://github.com/karpathy/llama2.c. The handler C++ source code for this examples can be found [here](./src/).
 
 ### Setup
 1. Follow the instructions in [README.md](../../../cpp/README.md) to build the TorchServe C++ backend.
@@ -29,7 +29,7 @@ echo '{
 
 5. Copy handle .so file
 
-While building the C++ backend the `libbabyllama_handler.so` file is generated in the [babyllama_handler](../../../cpp/test/resources/examples/babyllama/babyllama_handler) folder.
+While building the C++ backend the `libbabyllama_handler.so` file is generated in the [babyllama_handler](../../../cpp/_build/test/resources/examples/babyllama/babyllama_handler/) folder.
 
 ```bash
 cp ../../../cpp/_build/test/resources/examples/babyllama/babyllama_handler/libbabyllama_handler.so ./

examples/cpp/llamacpp/README.md

@@ -1,7 +1,7 @@
 ## Llama.cpp example
 
 This example used [llama.cpp](https://github.com/ggerganov/llama.cpp) to deploy a Llama-2-7B-Chat model using the TorchServe C++ backend.
-The handler C++ source code for this examples can be found [here](../../../cpp/src/examples/llamacpp/).
+The handler C++ source code for this examples can be found [here](./src/).
 
 ### Setup
 1. Follow the instructions in [README.md](../../../cpp/README.md) to build the TorchServe C++ backend.
@@ -28,7 +28,7 @@ echo '{
 
 5. Copy handle .so file
 
-While building the C++ backend the `libllamacpp_handler.so` file is generated in the [llamacpp_handler](../../../cpp/test/resources/examples/llamacpp/llamacpp_handler) folder.
+While building the C++ backend the `libllamacpp_handler.so` file is generated in the [llamacpp_handler](../../../cpp/_build/test/resources/examples/llamacpp/llamacpp_handler) folder.
 
 ```bash
 cp ../../../cpp/_build/test/resources/examples/llamacpp/llamacpp_handler/libllamacpp_handler.so ./