post-25.06: Update default branch (#8271)

Co-authored-by: Yingge He <[email protected]>

Author: mc-nv

Dockerfile.sdk

@@ -29,7 +29,7 @@
 #
 
 # Base image on the minimum Triton container
-ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:25.05-py3-min
+ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:25.06-py3-min
 
 ARG TRITON_CLIENT_REPO_SUBDIR=clientrepo
 ARG TRITON_PA_REPO_SUBDIR=perfanalyzerrepo

README.md

@@ -29,8 +29,8 @@
 
 >[!WARNING]
 >You are currently on the `main` branch which tracks under-development progress
->towards the next release. The current release is version [2.58.0](https://github.com/triton-inference-server/server/releases/latest)
->and corresponds to the 25.05 container release on NVIDIA GPU Cloud (NGC).
+>towards the next release. The current release is version [2.59.0](https://github.com/triton-inference-server/server/releases/latest)
+>and corresponds to the 25.06 container release on NVIDIA GPU Cloud (NGC).
 
 # Triton Inference Server
 
@@ -90,16 +90,16 @@ Inference Server with the
 
 ```bash
 # Step 1: Create the example model repository
-git clone -b r25.05 https://github.com/triton-inference-server/server.git
+git clone -b r25.06 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:25.05-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:25.06-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:25.05-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:25.06-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':

build.py

@@ -73,12 +73,12 @@
 DEFAULT_TRITON_VERSION_MAP = {
     "release_version": "2.60.0dev",
     "triton_container_version": "25.07dev",
-    "upstream_container_version": "25.05",
+    "upstream_container_version": "25.06",
     "ort_version": "1.22.0",
     "ort_openvino_version": "2025.1.0",
     "standalone_openvino_version": "2025.1.0",
     "dcgm_version": "3.3.6",
-    "vllm_version": "0.8.4",
+    "vllm_version": "0.9.0.1",
     "rhel_py_version": "3.12.3",
 }
 

deploy/aws/values.yaml

@@ -27,7 +27,7 @@
 replicaCount: 1
 
 image:
-  imageName: nvcr.io/nvidia/tritonserver:25.05-py3
+  imageName: nvcr.io/nvidia/tritonserver:25.06-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: "2.58.0"
+appVersion: "2.59.0"
 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:25.05-py3
+  imageName: nvcr.io/nvidia/tritonserver:25.06-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/r25.05/docs/user_guide/model_management.md
+    # See https://github.com/triton-inference-server/server/blob/r25.06/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/r25.05/README.md
+    # see https://github.com/triton-inference-server/server/blob/r25.06/README.md
     #  for more details
 
 service:

deploy/gcp/values.yaml

@@ -27,7 +27,7 @@
 replicaCount: 1
 
 image:
-  imageName: nvcr.io/nvidia/tritonserver:25.05-py3
+  imageName: nvcr.io/nvidia/tritonserver:25.06-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:25.05-py3-sdk
+  - image: nvcr.io/nvidia/tritonserver:25.06-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=2.58
-export MINOR_VERSION=2.58.0
-export NGC_VERSION=25.05-py3
+export MAJOR_VERSION=2.59
+export MINOR_VERSION=2.59.0
+export NGC_VERSION=25.06-py3
 
 docker pull nvcr.io/nvidia/$APP_NAME:$NGC_VERSION
 

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

@@ -25,7 +25,7 @@
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 apiVersion: v1
-appVersion: "2.58"
+appVersion: "2.59"
 description: Triton Inference Server
 name: triton-inference-server
-version: 2.58.0
+version: 2.59.0