version: TPRD-1695: Update version fro 25.09 release (#8386)

Author: mc-nv

Dockerfile.sdk

@@ -29,7 +29,7 @@
 #
 
 # Base image on the minimum Triton container
-ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:25.08-py3-min
+ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:25.09-py3-min
 
 ARG TRITON_CLIENT_REPO_SUBDIR=clientrepo
 ARG TRITON_REPO_ORGANIZATION=http://github.com/triton-inference-server

README.md

@@ -27,11 +27,6 @@
 -->
 [![License](https://img.shields.io/badge/License-BSD3-lightgrey.svg)](https://opensource.org/licenses/BSD-3-Clause)
 
->[!WARNING]
->You are currently on the `main` branch which tracks under-development progress
->towards the next release. The current release is version [2.60.0](https://github.com/triton-inference-server/server/releases/latest)
->and corresponds to the 25.08 container release on NVIDIA GPU Cloud (NGC).
-
 # Triton Inference Server
 
 Triton Inference Server is an open source inference serving software that
@@ -61,7 +56,7 @@ Major features include:
 - Provides [Backend API](https://github.com/triton-inference-server/backend) that
   allows adding custom backends and pre/post processing operations
 - Supports writing custom backends in python, a.k.a.
-  [Python-based backends.](https://github.com/triton-inference-server/backend/blob/main/docs/python_based_backends.md#python-based-backends)
+  [Python-based backends.](https://github.com/triton-inference-server/backend/blob/r25.09/docs/python_based_backends.md#python-based-backends)
 - Model pipelines using
   [Ensembling](docs/user_guide/architecture.md#ensemble-models) or [Business
   Logic Scripting
@@ -90,16 +85,16 @@ Inference Server with the
 
 ```bash
 # Step 1: Create the example model repository
-git clone -b r25.08 https://github.com/triton-inference-server/server.git
+git clone -b r25.09 https://github.com/triton-inference-server/server.git
 cd server/docs/examples
 ./fetch_models.sh
 
 # Step 2: Launch triton from the NGC Triton container
-docker run --gpus=1 --rm --net=host -v ${PWD}/model_repository:/models nvcr.io/nvidia/tritonserver:25.08-py3 tritonserver --model-repository=/models --model-control-mode explicit --load-model densenet_onnx
+docker run --gpus=1 --rm --net=host -v ${PWD}/model_repository:/models nvcr.io/nvidia/tritonserver:25.09-py3 tritonserver --model-repository=/models --model-control-mode explicit --load-model densenet_onnx
 
 # Step 3: Sending an Inference Request
 # In a separate console, launch the image_client example from the NGC Triton SDK container
-docker run -it --rm --net=host nvcr.io/nvidia/tritonserver:25.08-py3-sdk /workspace/install/bin/image_client -m densenet_onnx -c 3 -s INCEPTION /workspace/images/mug.jpg
+docker run -it --rm --net=host nvcr.io/nvidia/tritonserver:25.09-py3-sdk /workspace/install/bin/image_client -m densenet_onnx -c 3 -s INCEPTION /workspace/images/mug.jpg
 
 # Inference should return the following
 Image '/workspace/images/mug.jpg':
@@ -172,10 +167,10 @@ configuration](docs/user_guide/model_configuration.md) for the model.
   [Python](https://github.com/triton-inference-server/python_backend), and more
 - Not all the above backends are supported on every platform supported by Triton.
   Look at the
-  [Backend-Platform Support Matrix](https://github.com/triton-inference-server/backend/blob/main/docs/backend_platform_support_matrix.md)
+  [Backend-Platform Support Matrix](https://github.com/triton-inference-server/backend/blob/r25.09/docs/backend_platform_support_matrix.md)
   to learn which backends are supported on your target platform.
 - Learn how to [optimize performance](docs/user_guide/optimization.md) using the
-  [Performance Analyzer](https://github.com/triton-inference-server/perf_analyzer/blob/main/README.md)
+  [Performance Analyzer](https://github.com/triton-inference-server/perf_analyzer/blob/r25.09/README.md)
   and
   [Model Analyzer](https://github.com/triton-inference-server/model_analyzer)
 - Learn how to [manage loading and unloading models](docs/user_guide/model_management.md) in
@@ -189,14 +184,14 @@ A Triton *client* application sends inference and other requests to Triton. The
 [Python and C++ client libraries](https://github.com/triton-inference-server/client)
 provide APIs to simplify this communication.
 
-- Review client examples for [C++](https://github.com/triton-inference-server/client/blob/main/src/c%2B%2B/examples),
-  [Python](https://github.com/triton-inference-server/client/blob/main/src/python/examples),
-  and [Java](https://github.com/triton-inference-server/client/blob/main/src/java/src/main/java/triton/client/examples)
+- Review client examples for [C++](https://github.com/triton-inference-server/client/blob/r25.09/src/c%2B%2B/examples),
+  [Python](https://github.com/triton-inference-server/client/blob/r25.09/src/python/examples),
+  and [Java](https://github.com/triton-inference-server/client/blob/r25.09/src/java/src/main/java/triton/client/examples)
 - Configure [HTTP](https://github.com/triton-inference-server/client#http-options)
   and [gRPC](https://github.com/triton-inference-server/client#grpc-options)
   client options
 - Send input data (e.g. a jpeg image) directly to Triton in the [body of an HTTP
-  request without any additional metadata](https://github.com/triton-inference-server/server/blob/main/docs/protocol/extension_binary_data.md#raw-binary-request)
+  request without any additional metadata](https://github.com/triton-inference-server/server/blob/r25.09/docs/protocol/extension_binary_data.md#raw-binary-request)
 
 ### Extend Triton
 
@@ -205,7 +200,7 @@ designed for modularity and flexibility
 
 - [Customize Triton Inference Server container](docs/customization_guide/compose.md) for your use case
 - [Create custom backends](https://github.com/triton-inference-server/backend)
-  in either [C/C++](https://github.com/triton-inference-server/backend/blob/main/README.md#triton-backend-api)
+  in either [C/C++](https://github.com/triton-inference-server/backend/blob/r25.09/README.md#triton-backend-api)
   or [Python](https://github.com/triton-inference-server/python_backend)
 - Create [decoupled backends and models](docs/user_guide/decoupled_models.md) that can send
   multiple responses for a request or not send any responses for a request

build.py

@@ -73,12 +73,12 @@
 DEFAULT_TRITON_VERSION_MAP = {
     "release_version": "2.62.0dev",
     "triton_container_version": "25.10dev",
-    "upstream_container_version": "25.08",
+    "upstream_container_version": "25.09",
     "ort_version": "1.23.0",
     "ort_openvino_version": "2025.3.0",
     "standalone_openvino_version": "2025.3.0",
     "dcgm_version": "4.4.0-1",
-    "vllm_version": "0.9.2",
+    "vllm_version": "0.10.1.1",
     "rhel_py_version": "3.12.3",
 }
 

deploy/aws/values.yaml

@@ -27,7 +27,7 @@
 replicaCount: 1
 
 image:
-  imageName: nvcr.io/nvidia/tritonserver:25.08-py3
+  imageName: nvcr.io/nvidia/tritonserver:25.09-py3
   pullPolicy: IfNotPresent
   modelRepositoryPath: s3://triton-inference-server-repository/model_repository
   numGpus: 1

deploy/fleetcommand/Chart.yaml

@@ -26,7 +26,7 @@
 
 apiVersion: v1
 # appVersion is the Triton version; update when changing release
-appVersion: 2.60.0"
+appVersion: 2.61.0"
 description: Triton Inference Server (Fleet Command)
 name: triton-inference-server
 # version is the Chart version; update when changing anything in the chart

deploy/fleetcommand/values.yaml

@@ -27,7 +27,7 @@
 replicaCount: 1
 
 image:
-  imageName: nvcr.io/nvidia/tritonserver:25.08-py3
+  imageName: nvcr.io/nvidia/tritonserver:25.09-py3
   pullPolicy: IfNotPresent
   numGpus: 1
   serverCommand: tritonserver
@@ -47,13 +47,13 @@ image:
     #
     # To set model control mode, uncomment and configure below
     # TODO: Fix the following url, it is invalid
-    # See https://github.com/triton-inference-server/server/blob/r25.08/docs/user_guide/model_management.md
+    # See https://github.com/triton-inference-server/server/blob/r25.09/docs/user_guide/model_management.md
     #  for more details
     #- --model-control-mode=explicit|poll|none
     #
     # Additional server args
     #
-    # see https://github.com/triton-inference-server/server/blob/r25.08/README.md
+    # see https://github.com/triton-inference-server/server/blob/r25.09/README.md
     #  for more details
 
 service:

deploy/gcp/values.yaml

@@ -27,7 +27,7 @@
 replicaCount: 1
 
 image:
-  imageName: nvcr.io/nvidia/tritonserver:25.08-py3
+  imageName: nvcr.io/nvidia/tritonserver:25.09-py3
   pullPolicy: IfNotPresent
   modelRepositoryPath: gs://triton-inference-server-repository/model_repository
   numGpus: 1

deploy/gke-marketplace-app/benchmark/perf-analyzer-script/triton_client.yaml

@@ -33,7 +33,7 @@ metadata:
   namespace: default
 spec:
   containers:
-  - image: nvcr.io/nvidia/tritonserver:25.08-py3-sdk
+  - image: nvcr.io/nvidia/tritonserver:25.09-py3-sdk
     imagePullPolicy: Always
     name: nv-triton-client
     securityContext:

deploy/gke-marketplace-app/server-deployer/build_and_push.sh

@@ -27,9 +27,9 @@
 
 export REGISTRY=gcr.io/$(gcloud config get-value project | tr ':' '/')
 export APP_NAME=tritonserver
-export MAJOR_VERSION=2.60
-export MINOR_VERSION=2.60.0
-export NGC_VERSION=25.08-py3
+export MAJOR_VERSION=2.61
+export MINOR_VERSION=2.61.0
+export NGC_VERSION=25.09-py3
 
 docker pull nvcr.io/nvidia/$APP_NAME:$NGC_VERSION
 

deploy/gke-marketplace-app/server-deployer/chart/triton/Chart.yaml

@@ -28,4 +28,4 @@ apiVersion: v1
 appVersion: "2.60"
 description: Triton Inference Server
 name: triton-inference-server
-version: 2.60.0
+version: 2.61.0