[DO NOT MERGE] Update README and versions for 24.09

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:24.08-py3
-ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.08-py3-sdk
+ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.09-py3
+ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.09-py3-sdk
 
-ARG MODEL_ANALYZER_VERSION=1.44.0dev
-ARG MODEL_ANALYZER_CONTAINER_VERSION=24.09dev
+ARG MODEL_ANALYZER_VERSION=1.44.0
+ARG MODEL_ANALYZER_CONTAINER_VERSION=24.09
 FROM ${TRITONSDK_BASE_IMAGE} as sdk
 
 FROM $BASE_IMAGE

README.md

@@ -18,14 +18,6 @@ limitations under the License.
 
 # Triton Model Analyzer
 
-> [!Warning]
->
-> ##### LATEST RELEASE
->
-> You are currently on the `main` branch which tracks under-development progress towards the next release. <br>
-> The latest release of the Triton Model Analyzer is 1.43.0 and is available on branch
-> [r24.08](https://github.com/triton-inference-server/model_analyzer/tree/r24.08).
-
 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>
 
@@ -35,14 +27,14 @@ Triton Model Analyzer is a CLI tool which can help you find a more optimal confi
 
 - [Optuna Search](docs/config_search.md#optuna-search-mode) **_-ALPHA RELEASE-_** allows you to search for every parameter that can be specified in the model configuration, using a hyperparameter optimization framework. Please see the [Optuna](https://optuna.org/) website if you are interested in specific details on how the algorithm functions.
 
-- [Quick Search](docs/config_search.md#quick-search-mode) will **sparsely** search the [Max Batch Size](https://github.com/triton-inference-server/server/blob/main/docs/user_guide/model_configuration.md#maximum-batch-size),
-  [Dynamic Batching](https://github.com/triton-inference-server/server/blob/main/docs/user_guide/model_configuration.md#dynamic-batcher), and
-  [Instance Group](https://github.com/triton-inference-server/server/blob/main/docs/user_guide/model_configuration.md#instance-groups) spaces by utilizing a heuristic hill-climbing algorithm to help you quickly find a more optimal configuration
+- [Quick Search](docs/config_search.md#quick-search-mode) will **sparsely** search the [Max Batch Size](https://github.com/triton-inference-server/server/blob/r24.09/docs/user_guide/model_configuration.md#maximum-batch-size),
+  [Dynamic Batching](https://github.com/triton-inference-server/server/blob/r24.09/docs/user_guide/model_configuration.md#dynamic-batcher), and
+  [Instance Group](https://github.com/triton-inference-server/server/blob/r24.09/docs/user_guide/model_configuration.md#instance-groups) spaces by utilizing a heuristic hill-climbing algorithm to help you quickly find a more optimal configuration
 
 - [Automatic Brute Search](docs/config_search.md#automatic-brute-search) will **exhaustively** search the
-  [Max Batch Size](https://github.com/triton-inference-server/server/blob/main/docs/user_guide/model_configuration.md#maximum-batch-size),
-  [Dynamic Batching](https://github.com/triton-inference-server/server/blob/main/docs/user_guide/model_configuration.md#dynamic-batcher), and
-  [Instance Group](https://github.com/triton-inference-server/server/blob/main/docs/user_guide/model_configuration.md#instance-groups)
+  [Max Batch Size](https://github.com/triton-inference-server/server/blob/r24.09/docs/user_guide/model_configuration.md#maximum-batch-size),
+  [Dynamic Batching](https://github.com/triton-inference-server/server/blob/r24.09/docs/user_guide/model_configuration.md#dynamic-batcher), and
+  [Instance Group](https://github.com/triton-inference-server/server/blob/r24.09/docs/user_guide/model_configuration.md#instance-groups)
   parameters of your model configuration
 
 - [Manual Brute Search](docs/config_search.md#manual-brute-search) allows you to create manual sweeps for every parameter that can be specified in the model configuration

VERSION

@@ -1 +1 @@
-1.44.0dev
+1.44.0

docs/bls_quick_start.md

@@ -49,7 +49,7 @@ git pull origin main
 **1. Pull the SDK container:**
 
 ```
-docker pull nvcr.io/nvidia/tritonserver:24.08-py3-sdk
+docker pull nvcr.io/nvidia/tritonserver:24.09-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:24.08-py3-sdk
+      --net=host nvcr.io/nvidia/tritonserver:24.09-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:24.08-py3 ]
+[ triton_docker_image: <string> | default: nvcr.io/nvidia/tritonserver:24.09-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:24.08-py3-sdk
+docker pull nvcr.io/nvidia/tritonserver:24.09-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:24.08-py3-sdk
+      --net=host nvcr.io/nvidia/tritonserver:24.09-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: 24.08-py3
+    tag: 24.09-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:24.08-py3-sdk
+docker pull nvcr.io/nvidia/tritonserver:24.09-py3-sdk
 ```
 
 **2. Run the SDK container**
@@ -58,7 +58,7 @@ docker pull nvcr.io/nvidia/tritonserver:24.08-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:24.08-py3-sdk
+      --net=host nvcr.io/nvidia/tritonserver:24.09-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:24.08-py3-sdk
+docker pull nvcr.io/nvidia/tritonserver:24.09-py3-sdk
 ```
 
 **2. Run the SDK container**
@@ -58,7 +58,7 @@ docker pull nvcr.io/nvidia/tritonserver:24.08-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:24.08-py3-sdk
+      --net=host nvcr.io/nvidia/tritonserver:24.09-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: 24.08-py3
+    tag: 24.09-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:24.08-py3"
+DEFAULT_TRITON_DOCKER_IMAGE = "nvcr.io/nvidia/tritonserver:24.09-py3"
 DEFAULT_TRITON_HTTP_ENDPOINT = "localhost:8000"
 DEFAULT_TRITON_GRPC_ENDPOINT = "localhost:8001"
 DEFAULT_TRITON_METRICS_URL = "http://localhost:8002/metrics"