Update main post-23.05 release (#698)

* Update README and versions for 23.05 branch

* Update DCGM version (#692)

* Update Keyring URL location (#693)

* Set DCGM 2.4.7 version (#695)

Author: mc-nv

Dockerfile

@@ -12,8 +12,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:23.04-py3
-ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:23.04-py3-sdk
+ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:23.05-py3
+ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:23.05-py3-sdk
 
 ARG MODEL_ANALYZER_VERSION=1.29.0dev
 ARG MODEL_ANALYZER_CONTAINER_VERSION=23.06dev
@@ -27,7 +27,7 @@ ARG BASE_IMAGE
 ARG TRITONSDK_BASE_IMAGE
 
 # DCGM version to install for Model Analyzer
-ENV DCGM_VERSION=2.2.9
+ENV DCGM_VERSION=2.4.7
 
 # Ensure apt-get won't prompt for selecting options
 ENV DEBIAN_FRONTEND=noninteractive
@@ -42,7 +42,7 @@ RUN mkdir -p /opt/triton-model-analyzer
 
 RUN [ "$(uname -m)" != "x86_64" ] && arch="sbsa" || arch="x86_64" && \
     curl -o /tmp/cuda-keyring.deb \
-    https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/$arch/cuda-keyring_1.0-1_all.deb && \
+    https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/$arch/cuda-keyring_1.0-1_all.deb && \
     apt-get install /tmp/cuda-keyring.deb && rm /tmp/cuda-keyring.deb && \
     apt-get update && apt-get install -y --no-install-recommends software-properties-common && \
     apt-get install -y datacenter-gpu-manager=1:${DCGM_VERSION}; 

README.md

@@ -20,9 +20,9 @@ limitations under the License.
 
 **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 1.27.0 and is available on
+release of the Triton Model Analyzer is 1.28.0 and is available on
 branch
-[r23.04](https://github.com/triton-inference-server/model_analyzer/tree/r23.04).**
+[r23.05](https://github.com/triton-inference-server/model_analyzer/tree/r23.05).**
 
 Triton Model Analyzer is a CLI tool which can help you find a more optimal configuration, on a given piece of hardware, for single, multiple, ensemble, or BLS models running on a [Triton Inference Server](https://github.com/triton-inference-server/server/). Model Analyzer will also generate reports to help you better understand the trade-offs of the different configurations along with their compute and memory requirements.
 <br><br>

docs/config.md

@@ -153,7 +153,7 @@ cpu_only_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:23.04-py3 ]
+[ triton_docker_image: <string> | default: nvcr.io/nvidia/tritonserver:23.05-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: 23.04-py3
+    tag: 23.05-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:23.04-py3-sdk
+docker pull nvcr.io/nvidia/tritonserver:23.05-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:23.04-py3-sdk
+      --net=host nvcr.io/nvidia/tritonserver:23.05-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:23.04-py3-sdk
+docker pull nvcr.io/nvidia/tritonserver:23.05-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:23.04-py3-sdk
+      --net=host nvcr.io/nvidia/tritonserver:23.05-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: 23.04-py3
+    tag: 23.05-py3

model_analyzer/config/input/config_defaults.py

@@ -54,7 +54,7 @@
 DEFAULT_RUN_CONFIG_PROFILE_MODELS_CONCURRENTLY_ENABLE = False
 DEFAULT_REQUEST_RATE_SEARCH_ENABLE = False
 DEFAULT_TRITON_LAUNCH_MODE = 'local'
-DEFAULT_TRITON_DOCKER_IMAGE = 'nvcr.io/nvidia/tritonserver:23.04-py3'
+DEFAULT_TRITON_DOCKER_IMAGE = 'nvcr.io/nvidia/tritonserver:23.05-py3'
 DEFAULT_TRITON_HTTP_ENDPOINT = 'localhost:8000'
 DEFAULT_TRITON_GRPC_ENDPOINT = 'localhost:8001'
 DEFAULT_TRITON_METRICS_URL = 'http://localhost:8002/metrics'