Update README and versions for 21.11 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:21.10-py3
-ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:21.10-py3-sdk
+ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:21.11-py3
+ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:21.11-py3-sdk
 
-ARG MODEL_ANALYZER_VERSION=1.10.0dev
-ARG MODEL_ANALYZER_CONTAINER_VERSION=21.11dev
+ARG MODEL_ANALYZER_VERSION=1.10.0
+ARG MODEL_ANALYZER_CONTAINER_VERSION=21.11
 
 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 1.9.0 and is available on
-branch
-[r21.10](https://github.com/triton-inference-server/model_analyzer/tree/r21.10).**
-
 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 @@
-1.10.0dev
+1.10.0

docs/config.md

@@ -119,7 +119,7 @@ profile_models: <comma-delimited-string-list>
 [ perf_analyzer_max_auto_adjusts: <int> | default: 10 ]
 
 # Triton Docker image tag used when launching using Docker mode
-[ triton_docker_image: <string> | default: nvcr.io/nvidia/tritonserver:21.10-py3 ]
+[ triton_docker_image: <string> | default: nvcr.io/nvidia/tritonserver:21.11-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

@@ -26,15 +26,15 @@ Catalog](https://ngc.nvidia.com/catalog/containers/nvidia:tritonserver). You can
 pull and run the SDK container with the following commands:
 
 ```
-$ docker pull nvcr.io/nvidia/tritonserver:21.10-py3-sdk
+$ docker pull nvcr.io/nvidia/tritonserver:21.11-py3-sdk
 ```
 
 If you are not planning to run Model Analyzer with
 `--triton-launch-mode=docker`, You can run the SDK container with the following
 command: 
 
 ```
-$ docker run -it --gpus all --net=host nvcr.io/nvidia/tritonserver:21.10-py3-sdk
+$ docker run -it --gpus all --net=host nvcr.io/nvidia/tritonserver:21.11-py3-sdk
 ```
 
 You will need to build and install the Triton server binary inside the SDK
@@ -59,7 +59,7 @@ following:
 $ 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:21.10-py3-sdk
+      --net=host nvcr.io/nvidia/tritonserver:21.11-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: 21.10-py3
+    tag: 21.11-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: 21.10-py3
+    tag: 21.11-py3

model_analyzer/config/input/config_defaults.py

@@ -44,7 +44,7 @@
 DEFAULT_RUN_CONFIG_MAX_PREFERRED_BATCH_SIZE = 16
 DEFAULT_RUN_CONFIG_PREFERRED_BATCH_SIZE_DISABLE = False
 DEFAULT_TRITON_LAUNCH_MODE = 'local'
-DEFAULT_TRITON_DOCKER_IMAGE = 'nvcr.io/nvidia/tritonserver:21.10-py3'
+DEFAULT_TRITON_DOCKER_IMAGE = 'nvcr.io/nvidia/tritonserver:21.11-py3'
 DEFAULT_TRITON_HTTP_ENDPOINT = 'localhost:8000'
 DEFAULT_TRITON_GRPC_ENDPOINT = 'localhost:8001'
 DEFAULT_TRITON_METRICS_URL = 'http://localhost:8002/metrics'