Update README and versions for 1.41.0 / 24.06

Author: mc-nv

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:24.05-py3
-ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.05-py3-sdk
+ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.06-py3
+ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.06-py3-sdk
 
-ARG MODEL_ANALYZER_VERSION=1.41.0dev
-ARG MODEL_ANALYZER_CONTAINER_VERSION=24.06dev
+ARG MODEL_ANALYZER_VERSION=1.41.0
+ARG MODEL_ANALYZER_CONTAINER_VERSION=24.06
 FROM ${TRITONSDK_BASE_IMAGE} as sdk
 
 FROM $BASE_IMAGE

VERSION

@@ -1 +1 @@
-1.41.0dev
+1.41.0

docs/bls_quick_start.md

@@ -49,7 +49,7 @@ git pull origin main
 **1. Pull the SDK container:**
 
 ```
-docker pull nvcr.io/nvidia/tritonserver:24.05-py3-sdk
+docker pull nvcr.io/nvidia/tritonserver:24.06-py3-sdk
 ```
 
 **2. Run the SDK container**
@@ -59,7 +59,7 @@ docker run -it --gpus 1 \
       --shm-size 2G \
       -v /var/run/docker.sock:/var/run/docker.sock \
       -v $(pwd)/examples/quick-start:$(pwd)/examples/quick-start \
-      --net=host nvcr.io/nvidia/tritonserver:24.05-py3-sdk
+      --net=host nvcr.io/nvidia/tritonserver:24.06-py3-sdk
 ```
 
 **Important:** The example above uses a single GPU. If you are running on multiple GPUs, you may need to increase the shared memory size accordingly<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:24.05-py3 ]
+[ triton_docker_image: <string> | default: nvcr.io/nvidia/tritonserver:24.06-py3 ]
 
 # Triton Server HTTP endpoint url used by Model Analyzer client"
 [ triton_http_endpoint: <string> | default: localhost:8000 ]

docs/ensemble_quick_start.md

@@ -55,7 +55,7 @@ mkdir examples/quick-start/ensemble_add_sub/1
 **1. Pull the SDK container:**
 
 ```
-docker pull nvcr.io/nvidia/tritonserver:24.05-py3-sdk
+docker pull nvcr.io/nvidia/tritonserver:24.06-py3-sdk
 ```
 
 **2. Run the SDK container**
@@ -65,7 +65,7 @@ docker run -it --gpus 1 \
       --shm-size 1G \
       -v /var/run/docker.sock:/var/run/docker.sock \
       -v $(pwd)/examples/quick-start:$(pwd)/examples/quick-start \
-      --net=host nvcr.io/nvidia/tritonserver:24.05-py3-sdk
+      --net=host nvcr.io/nvidia/tritonserver:24.06-py3-sdk
 ```
 
 **Important:** The example above uses a single GPU. If you are running on multiple GPUs, you may need to increase the shared memory size accordingly<br><br>

docs/kubernetes_deploy.md

@@ -79,7 +79,7 @@ images:
 
   triton:
     image: nvcr.io/nvidia/tritonserver
-    tag: 24.05-py3
+    tag: 24.06-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.

docs/mm_quick_start.md

@@ -49,7 +49,7 @@ git pull origin main
 **1. Pull the SDK container:**
 
 ```
-docker pull nvcr.io/nvidia/tritonserver:24.05-py3-sdk
+docker pull nvcr.io/nvidia/tritonserver:24.06-py3-sdk
 ```
 
 **2. Run the SDK container**
@@ -58,7 +58,7 @@ docker pull nvcr.io/nvidia/tritonserver:24.05-py3-sdk
 docker run -it --gpus all \
       -v /var/run/docker.sock:/var/run/docker.sock \
       -v $(pwd)/examples/quick-start:$(pwd)/examples/quick-start \
-      --net=host nvcr.io/nvidia/tritonserver:24.05-py3-sdk
+      --net=host nvcr.io/nvidia/tritonserver:24.06-py3-sdk
 ```
 
 ## `Step 3:` Profile both models concurrently

docs/quick_start.md

@@ -49,7 +49,7 @@ git pull origin main
 **1. Pull the SDK container:**
 
 ```
-docker pull nvcr.io/nvidia/tritonserver:24.05-py3-sdk
+docker pull nvcr.io/nvidia/tritonserver:24.06-py3-sdk
 ```
 
 **2. Run the SDK container**
@@ -58,7 +58,7 @@ docker pull nvcr.io/nvidia/tritonserver:24.05-py3-sdk
 docker run -it --gpus all \
       -v /var/run/docker.sock:/var/run/docker.sock \
       -v $(pwd)/examples/quick-start:$(pwd)/examples/quick-start \
-      --net=host nvcr.io/nvidia/tritonserver:24.05-py3-sdk
+      --net=host nvcr.io/nvidia/tritonserver:24.06-py3-sdk
 ```
 
 ## `Step 3:` Profile the `add_sub` model

helm-chart/values.yaml

@@ -41,4 +41,4 @@ images:
 
   triton:
     image: nvcr.io/nvidia/tritonserver
-    tag: 24.05-py3
+    tag: 24.06-py3

model_analyzer/config/input/config_defaults.py

@@ -63,7 +63,7 @@
 DEFAULT_REQUEST_RATE_SEARCH_ENABLE = False
 DEFAULT_CONCURRENCY_SWEEP_DISABLE = False
 DEFAULT_TRITON_LAUNCH_MODE = "local"
-DEFAULT_TRITON_DOCKER_IMAGE = "nvcr.io/nvidia/tritonserver:24.05-py3"
+DEFAULT_TRITON_DOCKER_IMAGE = "nvcr.io/nvidia/tritonserver:24.06-py3"
 DEFAULT_TRITON_HTTP_ENDPOINT = "localhost:8000"
 DEFAULT_TRITON_GRPC_ENDPOINT = "localhost:8001"
 DEFAULT_TRITON_METRICS_URL = "http://localhost:8002/metrics"