diff --git a/Dockerfile b/Dockerfile index 7cf42f198..4c689a237 100644 --- a/Dockerfile +++ b/Dockerfile @@ -12,12 +12,11 @@ # See the License for the specific language governing permissions and # limitations under the License. -ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.02-py3 -ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.02-py3-sdk +ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.03-py3 +ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.03-py3-sdk ARG MODEL_ANALYZER_VERSION=1.39.0dev ARG MODEL_ANALYZER_CONTAINER_VERSION=24.04dev - FROM ${TRITONSDK_BASE_IMAGE} as sdk FROM $BASE_IMAGE diff --git a/README.md b/README.md index 404cb39f9..62d785c20 100644 --- a/README.md +++ b/README.md @@ -21,8 +21,8 @@ limitations under the License. > [!Warning] > ##### 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 1.37.0 and is available on branch -> [r24.02](https://github.com/triton-inference-server/model_analyzer/tree/r24.02). +> The latest release of the Triton Model Analyzer is 1.38.0 and is available on branch +> [r24.03](https://github.com/triton-inference-server/model_analyzer/tree/r24.03). 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. @@ -52,7 +52,7 @@ Triton Model Analyzer is a CLI tool which can help you find a more optimal confi - [BLS Model Search](docs/config_search.md#bls-model-search): Model Analyzer can help you find the optimal settings when profiling a BLS model, utilizing the [Quick Search](docs/config_search.md#quick-search-mode) algorithm -- [Multi-Model Search](docs/config_search.md#multi-model-search-mode): **EARLY ACCESS** - Model Analyzer can help you +- [Multi-Model Search](docs/config_search.md#multi-model-search-mode): Model Analyzer can help you find the optimal settings when profiling multiple concurrent models, utilizing the [Quick Search](docs/config_search.md#quick-search-mode) algorithm ### Other Features diff --git a/VERSION b/VERSION index 01ac5db94..ec65a10e8 100644 --- a/VERSION +++ b/VERSION @@ -1 +1 @@ -1.39.0dev +1.39.0dev \ No newline at end of file diff --git a/docs/bls_quick_start.md b/docs/bls_quick_start.md index 22eb406e0..33ee58f41 100644 --- a/docs/bls_quick_start.md +++ b/docs/bls_quick_start.md @@ -49,7 +49,7 @@ git pull origin main **1. Pull the SDK container:** ``` -docker pull nvcr.io/nvidia/tritonserver:24.02-py3-sdk +docker pull nvcr.io/nvidia/tritonserver:24.03-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:24.02-py3-sdk + --net=host nvcr.io/nvidia/tritonserver:24.03-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

diff --git a/docs/config.md b/docs/config.md index b08e933d8..2fccc32f5 100644 --- a/docs/config.md +++ b/docs/config.md @@ -153,7 +153,7 @@ cpu_only_composing_models: [ reload_model_disable: | default: false] # Triton Docker image tag used when launching using Docker mode -[ triton_docker_image: | default: nvcr.io/nvidia/tritonserver:24.02-py3 ] +[ triton_docker_image: | default: nvcr.io/nvidia/tritonserver:24.03-py3 ] # Triton Server HTTP endpoint url used by Model Analyzer client" [ triton_http_endpoint: | default: localhost:8000 ] diff --git a/docs/ensemble_quick_start.md b/docs/ensemble_quick_start.md index 23abb2bb4..20dd48e0f 100644 --- a/docs/ensemble_quick_start.md +++ b/docs/ensemble_quick_start.md @@ -55,7 +55,7 @@ mkdir examples/quick/ensemble_add_sub/1 **1. Pull the SDK container:** ``` -docker pull nvcr.io/nvidia/tritonserver:24.02-py3-sdk +docker pull nvcr.io/nvidia/tritonserver:24.03-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:24.02-py3-sdk + --net=host nvcr.io/nvidia/tritonserver:24.03-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

diff --git a/docs/kubernetes_deploy.md b/docs/kubernetes_deploy.md index ef63b4d15..0762e6f58 100644 --- a/docs/kubernetes_deploy.md +++ b/docs/kubernetes_deploy.md @@ -79,7 +79,7 @@ images: triton: image: nvcr.io/nvidia/tritonserver - tag: 24.02-py3 + tag: 24.03-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. diff --git a/docs/mm_quick_start.md b/docs/mm_quick_start.md index 6395f25a7..3fe44342b 100644 --- a/docs/mm_quick_start.md +++ b/docs/mm_quick_start.md @@ -49,7 +49,7 @@ git pull origin main **1. Pull the SDK container:** ``` -docker pull nvcr.io/nvidia/tritonserver:24.02-py3-sdk +docker pull nvcr.io/nvidia/tritonserver:24.03-py3-sdk ``` **2. Run the SDK container** @@ -58,7 +58,7 @@ docker pull nvcr.io/nvidia/tritonserver:24.02-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:24.02-py3-sdk + --net=host nvcr.io/nvidia/tritonserver:24.03-py3-sdk ``` ## `Step 3:` Profile both models concurrently diff --git a/docs/quick_start.md b/docs/quick_start.md index fc0cd87da..32e1ce737 100644 --- a/docs/quick_start.md +++ b/docs/quick_start.md @@ -49,7 +49,7 @@ git pull origin main **1. Pull the SDK container:** ``` -docker pull nvcr.io/nvidia/tritonserver:24.02-py3-sdk +docker pull nvcr.io/nvidia/tritonserver:24.03-py3-sdk ``` **2. Run the SDK container** @@ -58,7 +58,7 @@ docker pull nvcr.io/nvidia/tritonserver:24.02-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:24.02-py3-sdk + --net=host nvcr.io/nvidia/tritonserver:24.03-py3-sdk ``` ## `Step 3:` Profile the `add_sub` model diff --git a/helm-chart/values.yaml b/helm-chart/values.yaml index c15e98e44..d8eac5979 100644 --- a/helm-chart/values.yaml +++ b/helm-chart/values.yaml @@ -41,4 +41,4 @@ images: triton: image: nvcr.io/nvidia/tritonserver - tag: 24.02-py3 + tag: 24.03-py3 diff --git a/model_analyzer/config/input/config_defaults.py b/model_analyzer/config/input/config_defaults.py index 499b71b26..368aed008 100755 --- a/model_analyzer/config/input/config_defaults.py +++ b/model_analyzer/config/input/config_defaults.py @@ -56,7 +56,7 @@ 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:24.02-py3" +DEFAULT_TRITON_DOCKER_IMAGE = "nvcr.io/nvidia/tritonserver:24.03-py3" DEFAULT_TRITON_HTTP_ENDPOINT = "localhost:8000" DEFAULT_TRITON_GRPC_ENDPOINT = "localhost:8001" DEFAULT_TRITON_METRICS_URL = "http://localhost:8002/metrics"