From 1c4edadfa6fc536fbf7c5f11c18529f0f26283f8 Mon Sep 17 00:00:00 2001 From: "M. Chornyi" <99709299+mc-nv@users.noreply.github.com> Date: Wed, 8 Jul 2026 15:47:32 -0700 Subject: [PATCH] docs(versions): update README and versions for r26.07 Strip dev suffix for the 26.07 release: - VERSION 1.56.0dev -> 1.56.0 - Dockerfile MODEL_ANALYZER_VERSION 1.56.0, MODEL_ANALYZER_CONTAINER_VERSION 26.07 - bump Triton container train 26.06 -> 26.07 and blob refs r26.06 -> r26.07 --- Dockerfile | 8 ++++---- VERSION | 2 +- docs/bls_quick_start.md | 6 +++--- docs/config.md | 2 +- docs/ensemble_quick_start.md | 6 +++--- docs/kubernetes_deploy.md | 2 +- docs/mm_quick_start.md | 6 +++--- docs/quick_start.md | 6 +++--- helm-chart/values.yaml | 2 +- model_analyzer/config/input/config_defaults.py | 2 +- 10 files changed, 21 insertions(+), 21 deletions(-) diff --git a/Dockerfile b/Dockerfile index f820a85b..f62c01d6 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,11 +1,11 @@ # SPDX-FileCopyrightText: Copyright (c) 2020-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. # SPDX-License-Identifier: Apache-2.0 -ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:26.06-py3 -ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:26.06-py3-sdk +ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:26.07-py3 +ARG TRITONSDK_BASE_IMAGE=nvcr.io/nvidia/tritonserver:26.07-py3-sdk -ARG MODEL_ANALYZER_VERSION=1.56.0dev -ARG MODEL_ANALYZER_CONTAINER_VERSION=26.07dev +ARG MODEL_ANALYZER_VERSION=1.56.0 +ARG MODEL_ANALYZER_CONTAINER_VERSION=26.07 FROM ${TRITONSDK_BASE_IMAGE} AS sdk FROM ${BASE_IMAGE} diff --git a/VERSION b/VERSION index 08411587..3ebf789f 100644 --- a/VERSION +++ b/VERSION @@ -1 +1 @@ -1.56.0dev +1.56.0 diff --git a/docs/bls_quick_start.md b/docs/bls_quick_start.md index 7ee67f15..7600464e 100644 --- a/docs/bls_quick_start.md +++ b/docs/bls_quick_start.md @@ -38,7 +38,7 @@ git pull origin main **1. Pull the SDK container:** ``` -docker pull nvcr.io/nvidia/tritonserver:26.06-py3-sdk +docker pull nvcr.io/nvidia/tritonserver:26.07-py3-sdk ``` **2. Run the SDK container** @@ -48,7 +48,7 @@ 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:26.06-py3-sdk + --net=host nvcr.io/nvidia/tritonserver:26.07-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

@@ -57,7 +57,7 @@ docker run -it --gpus 1 \ --- -The [examples/quick-start](../examples/quick-start) directory is an example [Triton Model Repository](https://github.com/triton-inference-server/server/blob/r26.06/docs/user_guide/model_repository.md) that contains the BLS model `bls` which calculates the sum of two inputs using `add` model. +The [examples/quick-start](../examples/quick-start) directory is an example [Triton Model Repository](https://github.com/triton-inference-server/server/blob/r26.07/docs/user_guide/model_repository.md) that contains the BLS model `bls` which calculates the sum of two inputs using `add` model. An example model analyzer YAML config that performs a BLS model search diff --git a/docs/config.md b/docs/config.md index 1715cc9d..4e946b66 100644 --- a/docs/config.md +++ b/docs/config.md @@ -142,7 +142,7 @@ 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:26.06-py3 ] +[ triton_docker_image: | default: nvcr.io/nvidia/tritonserver:26.07-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 160a30b9..4debcee3 100644 --- a/docs/ensemble_quick_start.md +++ b/docs/ensemble_quick_start.md @@ -38,7 +38,7 @@ git pull origin main **1. Pull the SDK container:** ``` -docker pull nvcr.io/nvidia/tritonserver:26.06-py3-sdk +docker pull nvcr.io/nvidia/tritonserver:26.07-py3-sdk ``` **2. Run the SDK container** @@ -48,7 +48,7 @@ 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:26.06-py3-sdk + --net=host nvcr.io/nvidia/tritonserver:26.07-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

@@ -57,7 +57,7 @@ docker run -it --gpus 1 \ --- -The [examples/quick-start](../examples/quick-start) directory is an example [Triton Model Repository](https://github.com/triton-inference-server/server/blob/r26.06/docs/user_guide/model_repository.md) that contains the ensemble model `ensemble_add_sub`, which calculates the sum and difference of two inputs using `add` and `sub` models. +The [examples/quick-start](../examples/quick-start) directory is an example [Triton Model Repository](https://github.com/triton-inference-server/server/blob/r26.07/docs/user_guide/model_repository.md) that contains the ensemble model `ensemble_add_sub`, which calculates the sum and difference of two inputs using `add` and `sub` models. Run the Model Analyzer `profile` subcommand inside the container with: diff --git a/docs/kubernetes_deploy.md b/docs/kubernetes_deploy.md index 766d834f..86a94c39 100644 --- a/docs/kubernetes_deploy.md +++ b/docs/kubernetes_deploy.md @@ -68,7 +68,7 @@ images: triton: image: nvcr.io/nvidia/tritonserver - tag: 26.06-py3 + tag: 26.07-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 59920aae..f2462dd8 100644 --- a/docs/mm_quick_start.md +++ b/docs/mm_quick_start.md @@ -38,7 +38,7 @@ git pull origin main **1. Pull the SDK container:** ``` -docker pull nvcr.io/nvidia/tritonserver:26.06-py3-sdk +docker pull nvcr.io/nvidia/tritonserver:26.07-py3-sdk ``` **2. Run the SDK container** @@ -47,7 +47,7 @@ docker pull nvcr.io/nvidia/tritonserver:26.06-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:26.06-py3-sdk + --net=host nvcr.io/nvidia/tritonserver:26.07-py3-sdk ``` ## `Step 3:` Profile both models concurrently @@ -55,7 +55,7 @@ docker run -it --gpus all \ --- The [examples/quick-start](../examples/quick-start) directory is an example -[Triton Model Repository](https://github.com/triton-inference-server/server/blob/r26.06/docs/user_guide/model_repository.md) that contains two libtorch models: `add_sub` & `resnet50_python` +[Triton Model Repository](https://github.com/triton-inference-server/server/blob/r26.07/docs/user_guide/model_repository.md) that contains two libtorch models: `add_sub` & `resnet50_python` Run the Model Analyzer `profile` subcommand inside the container with: diff --git a/docs/quick_start.md b/docs/quick_start.md index 9160cdaa..0fe86589 100644 --- a/docs/quick_start.md +++ b/docs/quick_start.md @@ -38,7 +38,7 @@ git pull origin main **1. Pull the SDK container:** ``` -docker pull nvcr.io/nvidia/tritonserver:26.06-py3-sdk +docker pull nvcr.io/nvidia/tritonserver:26.07-py3-sdk ``` **2. Run the SDK container** @@ -47,7 +47,7 @@ docker pull nvcr.io/nvidia/tritonserver:26.06-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:26.06-py3-sdk + --net=host nvcr.io/nvidia/tritonserver:26.07-py3-sdk ``` ## `Step 3:` Profile the `add_sub` model @@ -55,7 +55,7 @@ docker run -it --gpus all \ --- The [examples/quick-start](../examples/quick-start) directory is an example -[Triton Model Repository](https://github.com/triton-inference-server/server/blob/r26.06/docs/user_guide/model_repository.md) that contains a simple libtorch model which calculates +[Triton Model Repository](https://github.com/triton-inference-server/server/blob/r26.07/docs/user_guide/model_repository.md) that contains a simple libtorch model which calculates the sum and difference of two inputs. Run the Model Analyzer `profile` subcommand inside the container with: diff --git a/helm-chart/values.yaml b/helm-chart/values.yaml index 172d9477..7519777d 100644 --- a/helm-chart/values.yaml +++ b/helm-chart/values.yaml @@ -26,4 +26,4 @@ images: triton: image: nvcr.io/nvidia/tritonserver - tag: 26.06-py3 + tag: 26.07-py3 diff --git a/model_analyzer/config/input/config_defaults.py b/model_analyzer/config/input/config_defaults.py index 54d75217..c5d44d82 100755 --- a/model_analyzer/config/input/config_defaults.py +++ b/model_analyzer/config/input/config_defaults.py @@ -52,7 +52,7 @@ DEFAULT_CONCURRENCY_SWEEP_DISABLE = False DEFAULT_DCGM_DISABLE = False DEFAULT_TRITON_LAUNCH_MODE = "local" -DEFAULT_TRITON_DOCKER_IMAGE = "nvcr.io/nvidia/tritonserver:26.06-py3" +DEFAULT_TRITON_DOCKER_IMAGE = "nvcr.io/nvidia/tritonserver:26.07-py3" DEFAULT_TRITON_HTTP_ENDPOINT = "localhost:8000" DEFAULT_TRITON_GRPC_ENDPOINT = "localhost:8001" DEFAULT_TRITON_METRICS_URL = "http://localhost:8002/metrics"