Update README and docs post-20.12 release (triton-inference-server#2498)

README.md

@@ -32,9 +32,9 @@
 
 **LATEST RELEASE: You are currently on the master branch which tracks
 under-development progress towards the next release. The latest
-release of the Triton Inference Server is 2.5.0 and is available on
+release of the Triton Inference Server is 2.6.0 and is available on
 branch
-[r20.11](https://github.com/triton-inference-server/server/tree/r20.11).**
+[r20.12](https://github.com/triton-inference-server/server/tree/r20.12).**
 
 Triton Inference Server provides a cloud and edge inferencing solution
 optimized for both CPUs and GPUs. Triton supports an HTTP/REST and
@@ -44,11 +44,11 @@ available as a shared library with a C API that allows the full
 functionality of Triton to be included directly in an
 application.
 
-The current release of the Triton Inference Server is 2.5.0 and
-corresponds to the 20.11 release of the tritonserver container on
+The current release of the Triton Inference Server is 2.6.0 and
+corresponds to the 20.12 release of the tritonserver container on
 [NVIDIA GPU Cloud (NGC)](https://ngc.nvidia.com). The branch for this
 release is
-[r20.11](https://github.com/triton-inference-server/server/tree/r20.11).
+[r20.12](https://github.com/triton-inference-server/server/tree/r20.12).
 
 ## Features
 
@@ -103,8 +103,8 @@ release is
 
 **The master branch documentation tracks the upcoming,
 under-development release and so may not be accurate for the current
-release of Triton. See the [r20.11
-documentation](https://github.com/triton-inference-server/server/tree/r20.11#documentation)
+release of Triton. See the [r20.12
+documentation](https://github.com/triton-inference-server/server/tree/r20.12#documentation)
 for the current release.**
 
 [Triton Architecture](docs/architecture.md) gives a high-level

deploy/single_server/values.yaml

@@ -27,7 +27,7 @@
 replicaCount: 1
 
 image:
-  imageName: nvcr.io/nvidia/tritonserver:20.11-py3
+  imageName: nvcr.io/nvidia/tritonserver:20.12-py3
   pullPolicy: IfNotPresent
   modelRepositoryPath: gs://triton-inference-server-repository/model_repository
   numGpus: 1

docs/build.md

@@ -61,8 +61,8 @@ $ ./build.py --build-dir=/tmp/citritonbuild --enable-logging --enable-stats --en
 If you are building on master/main branch then \<container tag\>
 should be set to "main". If you are building on a release branch you
 should set \<container tag\> to match the branch name. For example, if
-you are building on the r20.11 branch you should set \<container tag\>
-to be "r20.11". You can use a different \<container tag\> for a
+you are building on the r20.12 branch you should set \<container tag\>
+to be "r20.12". You can use a different \<container tag\> for a
 component to instead use the corresponding branch/tag in the
 build. For example, if you have a branch called "mybranch" in the
 [identity_backend](https://github.com/triton-inference-server/identity_backend)

docs/client_libraries.md

@@ -156,7 +156,7 @@ under-development version). The branch you use for the client build
 should match the version of Triton you are using.
 
 ```bash
-$ git checkout r20.11
+$ git checkout r20.12
 ```
 
 Then, issue the following command to build the C++ client library and
@@ -195,7 +195,7 @@ want to build (or the master branch if you want to build the
 under-development version).
 
 ```bash
-$ git checkout r20.11
+$ git checkout r20.12
 ```
 
 #### Ubuntu 20.04

docs/custom_operations.md

@@ -64,7 +64,7 @@ simple way to ensure you are using the correct version of TensorRT is
 to use the [NGC TensorRT
 container](https://ngc.nvidia.com/catalog/containers/nvidia:tensorrt)
 corresponding to the Triton container. For example, if you are using
-the 20.11 version of Triton, use the 20.11 version of the TensorRT
+the 20.12 version of Triton, use the 20.12 version of the TensorRT
 container.
 
 ## TensorFlow
@@ -108,7 +108,7 @@ simple way to ensure you are using the correct version of TensorFlow
 is to use the [NGC TensorFlow
 container](https://ngc.nvidia.com/catalog/containers/nvidia:tensorflow)
 corresponding to the Triton container. For example, if you are using
-the 20.11 version of Triton, use the 20.11 version of the TensorFlow
+the 20.12 version of Triton, use the 20.12 version of the TensorFlow
 container.
 
 ## PyTorch
@@ -152,7 +152,7 @@ simple way to ensure you are using the correct version of PyTorch is
 to use the [NGC PyTorch
 container](https://ngc.nvidia.com/catalog/containers/nvidia:pytorch)
 corresponding to the Triton container. For example, if you are using
-the 20.11 version of Triton, use the 20.11 version of the PyTorch
+the 20.12 version of Triton, use the 20.12 version of the PyTorch
 container.
 
 ## ONNX