Update README and versions for 23.04 branch

Author: tanmayv25

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:23.03-py3
-ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:23.03-py3-sdk
+ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:23.04-py3
+ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:23.04-py3-sdk
 
-ARG MODEL_ANALYZER_VERSION=1.27.0dev
-ARG MODEL_ANALYZER_CONTAINER_VERSION=23.04dev
+ARG MODEL_ANALYZER_VERSION=1.27.0
+ARG MODEL_ANALYZER_CONTAINER_VERSION=23.04
 
 FROM ${TRITONSDK_BASE_IMAGE} as sdk
 

VERSION

@@ -1 +1 @@
-1.27.0dev
+1.27.0

docs/config.md

@@ -147,7 +147,7 @@ bls_composing_models: <comma-delimited-string-list>
 [ reload_model_disable: <bool> | default: false]
 
 # Triton Docker image tag used when launching using Docker mode
-[ triton_docker_image: <string> | default: nvcr.io/nvidia/tritonserver:23.03-py3 ]
+[ triton_docker_image: <string> | default: nvcr.io/nvidia/tritonserver:23.04-py3 ]
 
 # Triton Server HTTP endpoint url used by Model Analyzer client"
 [ triton_http_endpoint: <string> | default: localhost:8000 ]

docs/kubernetes_deploy.md

@@ -79,7 +79,7 @@ images:
 
   triton:
     image: nvcr.io/nvidia/tritonserver
-    tag: 23.03-py3
+    tag: 23.04-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.

docs/mm_quick_start.md

@@ -49,7 +49,7 @@ git pull origin main
 **1. Pull the SDK container:**
 
 ```
-docker pull nvcr.io/nvidia/tritonserver:23.03-py3-sdk
+docker pull nvcr.io/nvidia/tritonserver:23.04-py3-sdk
 ```
 
 **2. Run the SDK container**
@@ -59,7 +59,7 @@ docker run -it --gpus all \
       -v /var/run/docker.sock:/var/run/docker.sock \
       -v $(pwd)/examples/quick-start:$(pwd)/examples/quick-start \
       -v <path-to-output-model-repo>:<path-to-output-model-repo> \
-      --net=host nvcr.io/nvidia/tritonserver:23.03-py3-sdk
+      --net=host nvcr.io/nvidia/tritonserver:23.04-py3-sdk
 ```
 
 **Replacing** `<path-to-output-model-repo>` with the

docs/quick_start.md

@@ -49,7 +49,7 @@ git pull origin main
 **1. Pull the SDK container:**
 
 ```
-docker pull nvcr.io/nvidia/tritonserver:23.03-py3-sdk
+docker pull nvcr.io/nvidia/tritonserver:23.04-py3-sdk
 ```
 
 **2. Run the SDK container**
@@ -59,7 +59,7 @@ docker run -it --gpus all \
       -v /var/run/docker.sock:/var/run/docker.sock \
       -v $(pwd)/examples/quick-start:$(pwd)/examples/quick-start \
       -v <path-to-output-model-repo>:<path-to-output-model-repo> \
-      --net=host nvcr.io/nvidia/tritonserver:23.03-py3-sdk
+      --net=host nvcr.io/nvidia/tritonserver:23.04-py3-sdk
 ```
 
 **Replacing** `<path-to-output-model-repo>` with the

helm-chart/values.yaml

@@ -41,4 +41,4 @@ images:
 
   triton:
     image: nvcr.io/nvidia/tritonserver
-    tag: 23.03-py3
+    tag: 23.04-py3

model_analyzer/config/input/config_defaults.py

@@ -49,7 +49,7 @@
 DEFAULT_RUN_CONFIG_SEARCH_MODE = 'brute'
 DEFAULT_RUN_CONFIG_PROFILE_MODELS_CONCURRENTLY_ENABLE = False
 DEFAULT_TRITON_LAUNCH_MODE = 'local'
-DEFAULT_TRITON_DOCKER_IMAGE = 'nvcr.io/nvidia/tritonserver:23.03-py3'
+DEFAULT_TRITON_DOCKER_IMAGE = 'nvcr.io/nvidia/tritonserver:23.04-py3'
 DEFAULT_TRITON_HTTP_ENDPOINT = 'localhost:8000'
 DEFAULT_TRITON_GRPC_ENDPOINT = 'localhost:8001'
 DEFAULT_TRITON_METRICS_URL = 'http://localhost:8002/metrics'