From 5063a99dcfedbb8624250338c868ad5312b60ff0 Mon Sep 17 00:00:00 2001 From: Misha Chornyi <99709299+mc-nv@users.noreply.github.com> Date: Fri, 8 Nov 2024 14:37:30 -0800 Subject: [PATCH 1/4] Update README and versions for 1.46.0 / 24.11 (#942) --- 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 2bda69a8..f1bc9ef1 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:24.10-py3 -ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.10-py3-sdk +ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.11-py3 +ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.11-py3-sdk ARG MODEL_ANALYZER_VERSION=1.47.0dev ARG MODEL_ANALYZER_CONTAINER_VERSION=24.12dev diff --git a/README.md b/README.md index b5c57636..3a825635 100644 --- a/README.md +++ b/README.md @@ -23,8 +23,8 @@ 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 1.45.0 and is available on branch -> [r24.10](https://github.com/triton-inference-server/model_analyzer/tree/r24.10). +> The latest release of the Triton Model Analyzer is 1.46.0 and is available on branch +> [r24.11](https://github.com/triton-inference-server/model_analyzer/tree/r24.11). 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 71aa9439..39c4c3d5 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:24.10-py3-sdk +docker pull nvcr.io/nvidia/tritonserver:24.11-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:24.10-py3-sdk + --net=host nvcr.io/nvidia/tritonserver:24.11-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 f25fc52f..132ace31 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:24.10-py3 ] +[ triton_docker_image: | default: nvcr.io/nvidia/tritonserver:24.11-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 68a4cbbc..2086a0b1 100644 --- a/docs/ensemble_quick_start.md +++ b/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:24.10-py3-sdk +docker pull nvcr.io/nvidia/tritonserver:24.11-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:24.10-py3-sdk + --net=host nvcr.io/nvidia/tritonserver:24.11-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 d0ab0326..d35a1972 100644 --- a/docs/kubernetes_deploy.md +++ b/docs/kubernetes_deploy.md @@ -79,7 +79,7 @@ images: triton: image: nvcr.io/nvidia/tritonserver - tag: 24.10-py3 + tag: 24.11-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 5da130a5..aeb798d6 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:24.10-py3-sdk +docker pull nvcr.io/nvidia/tritonserver:24.11-py3-sdk ``` **2. Run the SDK container** @@ -58,7 +58,7 @@ docker pull nvcr.io/nvidia/tritonserver:24.10-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:24.10-py3-sdk + --net=host nvcr.io/nvidia/tritonserver:24.11-py3-sdk ``` ## `Step 3:` Profile both models concurrently diff --git a/docs/quick_start.md b/docs/quick_start.md index 2655754d..8538a1b7 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:24.10-py3-sdk +docker pull nvcr.io/nvidia/tritonserver:24.11-py3-sdk ``` **2. Run the SDK container** @@ -58,7 +58,7 @@ docker pull nvcr.io/nvidia/tritonserver:24.10-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:24.10-py3-sdk + --net=host nvcr.io/nvidia/tritonserver:24.11-py3-sdk ``` ## `Step 3:` Profile the `add_sub` model diff --git a/helm-chart/values.yaml b/helm-chart/values.yaml index 427fb3e3..caf10481 100644 --- a/helm-chart/values.yaml +++ b/helm-chart/values.yaml @@ -41,4 +41,4 @@ images: triton: image: nvcr.io/nvidia/tritonserver - tag: 24.10-py3 + tag: 24.11-py3 diff --git a/model_analyzer/config/input/config_defaults.py b/model_analyzer/config/input/config_defaults.py index 6c520ec6..68d31fda 100755 --- a/model_analyzer/config/input/config_defaults.py +++ b/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:24.10-py3" +DEFAULT_TRITON_DOCKER_IMAGE = "nvcr.io/nvidia/tritonserver:24.11-py3" DEFAULT_TRITON_HTTP_ENDPOINT = "localhost:8000" DEFAULT_TRITON_GRPC_ENDPOINT = "localhost:8001" DEFAULT_TRITON_METRICS_URL = "http://localhost:8002/metrics" From 5fa372ca0ed59f112ffc32646af93ee6f011a995 Mon Sep 17 00:00:00 2001 From: Misha Chornyi <99709299+mc-nv@users.noreply.github.com> Date: Tue, 12 Nov 2024 21:27:00 -0800 Subject: [PATCH 2/4] Update base versions (#944) --- Dockerfile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Dockerfile b/Dockerfile index f1bc9ef1..dd81ddd9 100644 --- a/Dockerfile +++ b/Dockerfile @@ -26,7 +26,7 @@ ARG BASE_IMAGE ARG TRITONSDK_BASE_IMAGE # DCGM version to install for Model Analyzer -ENV DCGM_VERSION=3.2.6 +ENV DCGM_VERSION=3.3.6 # Ensure apt-get won't prompt for selecting options ENV DEBIAN_FRONTEND=noninteractive @@ -41,7 +41,7 @@ RUN mkdir -p /opt/triton-model-analyzer RUN [ "$(uname -m)" != "x86_64" ] && arch="sbsa" || arch="x86_64" && \ curl -o /tmp/cuda-keyring.deb \ - https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/$arch/cuda-keyring_1.0-1_all.deb && \ + https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/$arch/cuda-keyring_1.1-1_all.deb && \ apt-get install /tmp/cuda-keyring.deb && rm /tmp/cuda-keyring.deb && \ apt-get update && apt-get install -y --no-install-recommends software-properties-common && \ apt-get install -y datacenter-gpu-manager=1:${DCGM_VERSION}; From 264fcd559983e365aa3af72021022f6457ecceae Mon Sep 17 00:00:00 2001 From: Misha Chornyi <99709299+mc-nv@users.noreply.github.com> Date: Wed, 13 Nov 2024 07:22:27 -0800 Subject: [PATCH 3/4] Remove pip upgrade (#945) --- Dockerfile | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/Dockerfile b/Dockerfile index dd81ddd9..399b285b 100644 --- a/Dockerfile +++ b/Dockerfile @@ -70,8 +70,7 @@ RUN chmod +x /opt/triton-model-analyzer/nvidia_entrypoint.sh RUN chmod +x build_wheel.sh && \ ./build_wheel.sh perf_analyzer true && \ rm -f perf_analyzer -RUN python3 -m pip install --upgrade pip && \ - python3 -m pip install nvidia-pyindex && \ +RUN python3 -m pip install nvidia-pyindex && \ python3 -m pip install wheels/triton_model_analyzer-*-manylinux*.whl #Other pip packages RUN python3 -m pip install coverage From e8a5a8f04ae3b46976420346d23ccedee777e174 Mon Sep 17 00:00:00 2001 From: Misha Chornyi <99709299+mc-nv@users.noreply.github.com> Date: Thu, 21 Nov 2024 12:34:33 -0800 Subject: [PATCH 4/4] Lock grpcio version (#946) --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index a95c2798..af59c407 100644 --- a/requirements.txt +++ b/requirements.txt @@ -16,7 +16,7 @@ cryptography>=3.3.2 distro>=1.5.0 docker>=4.3.1 gevent>=22.08.0 -grpcio>=1.41.0 +grpcio>=1.41.0,<1.68 httplib2>=0.19.0 importlib_metadata>=7.1.0 matplotlib>=3.3.4