fix metrics readme (#72)

Fix README dead links 
Test added here triton-inference-server/server#4926

README.md

@@ -135,7 +135,7 @@ backends](#backends).
 Yes. See [Backend Shared Library](#backend-shared-library) for general
 information about how the shared library implementing a backend is
 managed by Triton, and [Triton with Unsupported and Custom
-Backends](https://github.com/triton-inference-server/server/blob/main/docs/compose.md#triton-with-unsupported-and-custom-backends)
+Backends](https://github.com/triton-inference-server/server/blob/main/docs/customization_guide/compose.md#triton-with-unsupported-and-custom-backends)
 for documentation on how to add your backend to the released Triton
 Docker image. For a standard install the globally available backends
 are in /opt/tritonserver/backends.
@@ -190,7 +190,7 @@ to override the default.
 Typically you will install your backend into the global backend
 directory. For example, if using Triton Docker images you can follow
 the instructions in [Triton with Unsupported and Custom
-Backends](https://github.com/triton-inference-server/server/blob/main/docs/compose.md#triton-with-unsupported-and-custom-backends). Continuing
+Backends](https://github.com/triton-inference-server/server/blob/main/docs/customization_guide/compose.md#triton-with-unsupported-and-custom-backends). Continuing
 the example of a backend names "mybackend", you would install into the
 Triton image as:
 
@@ -508,7 +508,7 @@ what can be acheived from decoupled API.
 Study documentation of these TRTIONBACKEND_* functions in
 [tritonbackend.h](https://github.com/triton-inference-server/core/blob/main/include/triton/core/tritonbackend.h)
 for more details on these APIs. Read
-[Decoupled Backends and Models](https://github.com/triton-inference-server/server/blob/main/docs/decoupled_models.md)
+[Decoupled Backends and Models](https://github.com/triton-inference-server/server/blob/main/docs/user_guide/decoupled_models.md)
 for more details on how to host a decoupled model.
 
 ## Build the Backend Utilities

docs/backend_platform_support_matrix.md

@@ -79,7 +79,7 @@ Following backends are currently supported on Jetson Jetpack:
 | Python[^1]   |  :x: GPU <br/> :heavy_check_mark: CPU    |
 
 
-Look at the [Triton Inference Server Support for Jetson and JetPack](https://github.com/triton-inference-server/server/blob/main/docs/jetson.md).
+Look at the [Triton Inference Server Support for Jetson and JetPack](https://github.com/triton-inference-server/server/blob/main/docs/user_guide/jetson.md).
 
 
 ## AWS Inferentia

examples/README.md

@@ -47,10 +47,10 @@ multiple responses per request.
 [*stateful*](https://github.com/triton-inference-server/stateful_backend)
 backend shows an example of how a backend can manage model state
 tensors on the server-side for the [sequence
-batcher](https://github.com/triton-inference-server/server/blob/main/docs/model_configuration.md#sequence-batcher)
+batcher](https://github.com/triton-inference-server/server/blob/main/docs/user_guide/model_configuration.md#sequence-batcher)
 to avoid transferring state tensors between client and server. Triton
 also implements [Implicit State
-Management](https://github.com/triton-inference-server/server/blob/main/docs/architecture.md#implicit-state-management)
+Management](https://github.com/triton-inference-server/server/blob/main/docs/user_guide/architecture.md#implicit-state-management)
 which allows backends to behave in a stateless manner and leave the
 state management to Triton.
 
@@ -74,9 +74,9 @@ backend and the use of the [Triton Backend
 API](../README.md#triton-backend-api) and the backend
 utilities. Before reading the source code, make sure you understand
 the concepts associated with Triton backend abstractions
-[TRITONBACKEND_Backend](../README.md#tritonbackend-backend),
-[TRITONBACKEND_Model](../README.md#tritonbackend-model), and
-[TRITONBACKEND_ModelInstance](../README.md#tritonbackend-modelinstance).
+[TRITONBACKEND_Backend](../README.md#tritonbackend_backend),
+[TRITONBACKEND_Model](../README.md#tritonbackend_model), and
+[TRITONBACKEND_ModelInstance](../README.md#tritonbackend_modelinstance).
 
 The *minimal* backend does not do any interesting operation, it simply
 copies a single input tensor to a single output tensor, but it does
@@ -160,10 +160,10 @@ I1215 23:46:00.250284 68 server.cc:589]
 
 The models are identical except that the *batching* model enabled the
 [dynamic
-batcher](https://github.com/triton-inference-server/server/blob/main/docs/model_configuration.md#dynamic-batcher)
+batcher](https://github.com/triton-inference-server/server/blob/main/docs/user_guide/model_configuration.md#dynamic-batcher)
 and supports batch sizes up to 8. Note that the *batching* model sets
 the [batch
-delay](https://github.com/triton-inference-server/server/blob/main/docs/model_configuration.md#delayed-batching)
+delay](https://github.com/triton-inference-server/server/blob/main/docs/user_guide/model_configuration.md#delayed-batching)
 to 5 seconds so that the example client described below can
 demonstrate how the *minimal* backend receives a batch of requests.
 
@@ -231,9 +231,9 @@ backend and the use of the [Triton Backend
 API](../README.md#triton-backend-api) and the backend
 utilities. Before reading the source code, make sure you understand
 the concepts associated with Triton backend abstractions
-[TRITONBACKEND_Backend](../README.md#tritonbackend-backend),
-[TRITONBACKEND_Model](../README.md#tritonbackend-model), and
-[TRITONBACKEND_ModelInstance](../README.md#tritonbackend-modelinstance).
+[TRITONBACKEND_Backend](../README.md#tritonbackend_backend),
+[TRITONBACKEND_Model](../README.md#tritonbackend_model), and
+[TRITONBACKEND_ModelInstance](../README.md#tritonbackend_modelinstance).
 
 The *recommended* backend improves the [*minimal*
 backend](#minimal-triton-backend) to include the following features
@@ -248,7 +248,7 @@ which should be present in any robust backend implementation:
 * Uses the Triton backend metric APIs to record statistics about
   requests executing in the backend. These metrics can then we queried
   using the Triton
-  [metrics](https://github.com/triton-inference-server/server/blob/main/docs/metrics.md)
+  [metrics](https://github.com/triton-inference-server/server/blob/main/docs/user_guide/metrics.md)
   and
   [statistics](https://github.com/triton-inference-server/server/blob/main/docs/protocol/extension_statistics.md)
   APIs.
@@ -361,7 +361,7 @@ $ curl localhost:8002/metrics
 
 The output will be metric values in Prometheus data format. The
 [metrics
-documentation](https://github.com/triton-inference-server/server/blob/main/docs/metrics.md)
+documentation](https://github.com/triton-inference-server/server/blob/main/docs/user_guide/metrics.md)
 gives a description of these metric values.
 
 ```
@@ -400,7 +400,7 @@ enhance the capabilities of your backend.
 #### Automatically Model Configuration Generation
 
 [Automatic model configuration
-generation](https://github.com/triton-inference-server/server/blob/main/docs/model_configuration.md#auto-generated-model-configuration)
+generation](https://github.com/triton-inference-server/server/blob/main/docs/user_guide/model_configuration.md#auto-generated-model-configuration)
 is enabled by the backend implementing the appropriate logic (for
 example, in a function called AutoCompleteConfig) during
 TRITONBACKEND_ModelInitialize. For the *recommended* backend you would

examples/backends/bls/README.md

@@ -32,7 +32,7 @@ The [*BLS*](../bls) backend demonstrates using in-process C-API to
 execute inferences within the backend. This backend serves as an example to
 backend developers for implementing their own custom pipeline in C++.
 For Python use cases, please refer to 
-[Business Logic Scripting](https://github.com/triton-inference-server/python_backend#business-logic-scripting)
+[Business Logic Scripting](https://github.com/triton-inference-server/python_backend/blob/main/README.md#business-logic-scripting)
 section in Python backend.
 
 The source code for the *bls* backend is contained in
@@ -42,8 +42,7 @@ The source code for the *bls* backend is contained in
 implementation. The content of this file is not BLS specific. It only includes
 the required Triton backend functions that is standard for any backend
 implementation. The BLS logic is set off in the
-[`TRITONBACKEND_ModelInstanceExecute`](./src/backend.cc#L316).
-function.
+`TRITONBACKEND_ModelInstanceExecute` with lines `bls_executor.Execute(requests[r], &responses[r]);`.
 
 * [bls.h](./src/bls.h) is where the BLS (class `BLSExecutor`) of
 this example is located. You can refer to this file to see how to interact with
@@ -55,7 +54,7 @@ are not BLS dependent are located.
 The source code contains extensive documentation describing the operation of
 the backend and the use of the
 [Triton Backend API](../../../README.md#triton-backend-api) and the
-[Triton Server API](https://github.com/triton-inference-server/server/blob/main/docs/inference_protocols.md#in-process-triton-server-api).
+[Triton Server API](https://github.com/triton-inference-server/server/blob/main/docs/customization_guide/inference_protocols.md#in-process-triton-server-api).
 Before reading the source code, make sure you understand
 the concepts associated with Triton backend abstractions
 [TRITONBACKEND_Backend](../../../README.md#tritonbackend_backend),
@@ -70,9 +69,9 @@ construct the final inference response object using these tensors.
 There are some self-imposed limitations that were made for the simplicity of
 this example:
 1. This backend does not support batching.
-1. This backend does not support decoupled models.
-1. This backend does not support GPU tensors.
-1. The model configuraion should be strictly set as the comments described in
+2. This backend does not support decoupled models.
+3. This backend does not support GPU tensors.
+4. The model configuraion should be strictly set as the comments described in
 [backend.cc](./src/backend.cc).
 
 You can implement your custom backend that is not limited to the limitations