From 462e0189529faf664432302cd789e8dcb4444c9f Mon Sep 17 00:00:00 2001 From: Misha Chornyi <99709299+mc-nv@users.noreply.github.com> Date: Sat, 2 Mar 2024 14:27:02 -0800 Subject: [PATCH] Update 'main' post-24.02 (#831) * Update README and versions for 1.37.0 / 24.02 (#824) * Update README.md post 24.02 --- Dockerfile | 4 ++-- README.md | 4 ++-- docs/bls_quick_start.md | 4 ++-- docs/config.md | 2 +- docs/ensemble_quick_start.md | 4 ++-- docs/kubernetes_deploy.md | 2 +- docs/mm_quick_start.md | 4 ++-- docs/quick_start.md | 4 ++-- helm-chart/values.yaml | 2 +- model_analyzer/config/input/config_defaults.py | 2 +- 10 files changed, 16 insertions(+), 16 deletions(-) diff --git a/Dockerfile b/Dockerfile index f80579ab4..eaff70e7d 100644 --- a/Dockerfile +++ b/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:24.01-py3 -ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.01-py3-sdk +ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.02-py3 +ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.02-py3-sdk ARG MODEL_ANALYZER_VERSION=1.38.0dev ARG MODEL_ANALYZER_CONTAINER_VERSION=24.03dev diff --git a/README.md b/README.md index b2764c4e3..404cb39f9 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 1.36.0 and is available on branch -> [r24.01](https://github.com/triton-inference-server/model_analyzer/tree/r24.01). +> 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). 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. diff --git a/docs/bls_quick_start.md b/docs/bls_quick_start.md index 432b6876f..22eb406e0 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:24.01-py3-sdk +docker pull nvcr.io/nvidia/tritonserver:24.02-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:24.01-py3-sdk + --net=host nvcr.io/nvidia/tritonserver:24.02-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 bc091e86b..b08e933d8 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:24.01-py3 ] +[ triton_docker_image: | default: nvcr.io/nvidia/tritonserver:24.02-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 4d2ff8501..23abb2bb4 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:24.01-py3-sdk +docker pull nvcr.io/nvidia/tritonserver:24.02-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:24.01-py3-sdk + --net=host nvcr.io/nvidia/tritonserver:24.02-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 db0b6230d..ef63b4d15 100644 --- a/docs/kubernetes_deploy.md +++ b/docs/kubernetes_deploy.md @@ -79,7 +79,7 @@ images: triton: image: nvcr.io/nvidia/tritonserver - tag: 24.01-py3 + tag: 24.02-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 058054e7c..6395f25a7 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:24.01-py3-sdk +docker pull nvcr.io/nvidia/tritonserver:24.02-py3-sdk ``` **2. Run the SDK container** @@ -58,7 +58,7 @@ docker pull nvcr.io/nvidia/tritonserver:24.01-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:24.01-py3-sdk + --net=host nvcr.io/nvidia/tritonserver:24.02-py3-sdk ``` ## `Step 3:` Profile both models concurrently diff --git a/docs/quick_start.md b/docs/quick_start.md index 55d4340af..fc0cd87da 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:24.01-py3-sdk +docker pull nvcr.io/nvidia/tritonserver:24.02-py3-sdk ``` **2. Run the SDK container** @@ -58,7 +58,7 @@ docker pull nvcr.io/nvidia/tritonserver:24.01-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:24.01-py3-sdk + --net=host nvcr.io/nvidia/tritonserver:24.02-py3-sdk ``` ## `Step 3:` Profile the `add_sub` model diff --git a/helm-chart/values.yaml b/helm-chart/values.yaml index 5efae3c9c..c15e98e44 100644 --- a/helm-chart/values.yaml +++ b/helm-chart/values.yaml @@ -41,4 +41,4 @@ images: triton: image: nvcr.io/nvidia/tritonserver - tag: 24.01-py3 + tag: 24.02-py3 diff --git a/model_analyzer/config/input/config_defaults.py b/model_analyzer/config/input/config_defaults.py index 21befaa71..499b71b26 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:24.01-py3" +DEFAULT_TRITON_DOCKER_IMAGE = "nvcr.io/nvidia/tritonserver:24.02-py3" DEFAULT_TRITON_HTTP_ENDPOINT = "localhost:8000" DEFAULT_TRITON_GRPC_ENDPOINT = "localhost:8001" DEFAULT_TRITON_METRICS_URL = "http://localhost:8002/metrics"