Update README and versions for 21.06 branch

Author: dzier

Dockerfile

@@ -12,11 +12,11 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:21.05-py3
-ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:21.05-py3-sdk
+ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:21.06-py3
+ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:21.06-py3-sdk
 
-ARG MODEL_ANALYZER_VERSION=1.5.0dev
-ARG MODEL_ANALYZER_CONTAINER_VERSION=21.06dev
+ARG MODEL_ANALYZER_VERSION=1.5.0
+ARG MODEL_ANALYZER_CONTAINER_VERSION=21.06
 
 FROM ${TRITONSDK_BASE_IMAGE} as sdk
 

README.md

@@ -18,12 +18,6 @@ limitations under the License.
 
 # Triton Model Analyzer
 
-**LATEST RELEASE: You are currently on the main branch which tracks
-under-development progress towards the next release. The latest
-release of the Triton Model Analyzer is 1.4.0 and is available on
-branch
-[r21.05](https://github.com/triton-inference-server/model_analyzer/tree/r21.05).**
-
 Triton Model Analyzer is a CLI tool to help with better understanding of the
 compute and memory requirements of the Triton Inference Server models. These
 reports will help the user better understand the trade-offs in different

VERSION

@@ -1 +1 @@
-1.5.0dev
+1.5.0

docs/config.md

@@ -107,7 +107,7 @@ profile_models: <comma-delimited-string-list>
 [ perf_output: <bool> | default: false ]
 
 # Triton Docker image tag used when launching using Docker mode
-[ triton_docker_image: <string> | default: nvcr.io/nvidia/tritonserver:21.05-py3 ]
+[ triton_docker_image: <string> | default: nvcr.io/nvidia/tritonserver:21.06-py3 ]
 
 # Triton Server HTTP endpoint url used by Model Analyzer client. Will be ignored if server-launch-mode is not 'remote'".
 [ triton_http_endpoint: <string> | default: localhost:8000 ]

docs/install.md

@@ -24,15 +24,15 @@ There are three ways to use Triton Model Analyzer:
    can pull and run the SDK container with the following commands:
 
    ```
-   $ docker pull nvcr.io/nvidia/tritonserver:21.05-py3-sdk
+   $ docker pull nvcr.io/nvidia/tritonserver:21.06-py3-sdk
    ```
 
    If you are not planning to run Model Analyzer with
    `--triton-launch-mode=docker` you can run the container with the following
    command:
 
    ```
-   $ docker run -it --gpus all --net=host nvcr.io/nvidia/tritonserver:21.05-py3-sdk
+   $ docker run -it --gpus all --net=host nvcr.io/nvidia/tritonserver:21.06-py3-sdk
    ```
 
    If you intend to use `--triton-launch-mode=docker`, you will need to mount
@@ -51,7 +51,7 @@ There are three ways to use Triton Model Analyzer:
    $ docker run -it --gpus all \
         -v /var/run/docker.sock:/var/run/docker.sock \
         -v <path-to-output-model-repo>:<path-to-output-model-repo> \
-        --net=host nvcr.io/nvidia/tritonserver:21.05-py3-sdk
+        --net=host nvcr.io/nvidia/tritonserver:21.06-py3-sdk
    ```
 
    Model Analyzer uses `pdfkit` for report generation. If you are running Model

docs/kubernetes_deploy.md

@@ -79,7 +79,7 @@ images:
 
   triton:
     image: nvcr.io/nvidia/tritonserver
-    tag: 21.05-py3
+    tag: 21.06-py3
 ```
 
 The model analyzer executable uses the config file defined in `helm-chart/templates/config-map.yaml`. This config can be modified to supply arguments to model analyzer. Only the content under the `config.yaml` section of the file should be modified.

helm-chart/values.yaml

@@ -41,4 +41,4 @@ images:
 
   triton:
     image: nvcr.io/nvidia/tritonserver
-    tag: 21.05-py3
+    tag: 21.06-py3

tests/test_perf_analyzer.py

@@ -36,7 +36,7 @@
 MODEL_REPOSITORY_PATH = '/model_analyzer/models'
 PERF_BIN_PATH = 'perf_analyzer'
 TRITON_LOCAL_BIN_PATH = 'test_path'
-TRITON_VERSION = '21.05'
+TRITON_VERSION = '21.06'
 TEST_MODEL_NAME = 'test_model'
 TEST_CONCURRENCY_RANGE = '1:16:2'
 CONFIG_TEST_ARG = 'sync'