diff --git a/Dockerfile.sdk b/Dockerfile.sdk
index 33414c3fe4..d1c4b5a189 100644
--- a/Dockerfile.sdk
+++ b/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
diff --git a/README.md b/README.md
index 2de74ae96a..057e58e8f9 100644
--- a/README.md
+++ b/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':
diff --git a/build.py b/build.py
index 3da4ad89e3..ff069c7d20 100755
--- a/build.py
+++ b/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",
 }
 
diff --git a/deploy/aws/values.yaml b/deploy/aws/values.yaml
index cddaaaf3a6..c24b0ed7b8 100644
--- a/deploy/aws/values.yaml
+++ b/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
diff --git a/deploy/fleetcommand/Chart.yaml b/deploy/fleetcommand/Chart.yaml
index 0664a5d959..b819cbb4a5 100644
--- a/deploy/fleetcommand/Chart.yaml
+++ b/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
diff --git a/deploy/fleetcommand/values.yaml b/deploy/fleetcommand/values.yaml
index b4044b795a..d2300ef421 100644
--- a/deploy/fleetcommand/values.yaml
+++ b/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:
diff --git a/deploy/gcp/values.yaml b/deploy/gcp/values.yaml
index 3770934cc8..73948fb39d 100644
--- a/deploy/gcp/values.yaml
+++ b/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
diff --git a/deploy/gke-marketplace-app/benchmark/perf-analyzer-script/triton_client.yaml b/deploy/gke-marketplace-app/benchmark/perf-analyzer-script/triton_client.yaml
index 38a65ed8e8..8be23e0f2c 100644
--- a/deploy/gke-marketplace-app/benchmark/perf-analyzer-script/triton_client.yaml
+++ b/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:
diff --git a/deploy/gke-marketplace-app/server-deployer/build_and_push.sh b/deploy/gke-marketplace-app/server-deployer/build_and_push.sh
index 6cb6f76e0a..b31804b9a2 100755
--- a/deploy/gke-marketplace-app/server-deployer/build_and_push.sh
+++ b/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
 
diff --git a/deploy/gke-marketplace-app/server-deployer/chart/triton/Chart.yaml b/deploy/gke-marketplace-app/server-deployer/chart/triton/Chart.yaml
index 5011733bbc..3206248935 100644
--- a/deploy/gke-marketplace-app/server-deployer/chart/triton/Chart.yaml
+++ b/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
diff --git a/deploy/gke-marketplace-app/server-deployer/chart/triton/values.yaml b/deploy/gke-marketplace-app/server-deployer/chart/triton/values.yaml
index ed69180192..52b1ab2f21 100644
--- a/deploy/gke-marketplace-app/server-deployer/chart/triton/values.yaml
+++ b/deploy/gke-marketplace-app/server-deployer/chart/triton/values.yaml
@@ -31,14 +31,14 @@ maxReplicaCount: 3
 tritonProtocol: HTTP
 # HPA GPU utilization autoscaling target
 HPATargetAverageValue: 85
-modelRepositoryPath: gs://triton_sample_models/25.05
-publishedVersion: '2.58.0'
+modelRepositoryPath: gs://triton_sample_models/25.06
+publishedVersion: '2.59.0'
 gcpMarketplace: true
 
 image:
   registry: gcr.io
   repository: nvidia-ngc-public/tritonserver
-  tag: 25.05-py3
+  tag: 25.06-py3
   pullPolicy: IfNotPresent
   # modify the model repository here to match your GCP storage bucket
   numGpus: 1
diff --git a/deploy/gke-marketplace-app/server-deployer/data-test/schema.yaml b/deploy/gke-marketplace-app/server-deployer/data-test/schema.yaml
index 2c55441213..36ba6b6a63 100644
--- a/deploy/gke-marketplace-app/server-deployer/data-test/schema.yaml
+++ b/deploy/gke-marketplace-app/server-deployer/data-test/schema.yaml
@@ -27,7 +27,7 @@
 x-google-marketplace:
   schemaVersion: v2
   applicationApiVersion: v1beta1
-  publishedVersion: '2.58.0'
+  publishedVersion: '2.59.0'
   publishedVersionMetadata:
     releaseNote: >-
       Initial release.
diff --git a/deploy/gke-marketplace-app/server-deployer/schema.yaml b/deploy/gke-marketplace-app/server-deployer/schema.yaml
index 68c171d28a..629303952d 100644
--- a/deploy/gke-marketplace-app/server-deployer/schema.yaml
+++ b/deploy/gke-marketplace-app/server-deployer/schema.yaml
@@ -27,7 +27,7 @@
 x-google-marketplace:
   schemaVersion: v2
   applicationApiVersion: v1beta1
-  publishedVersion: '2.58.0'
+  publishedVersion: '2.59.0'
   publishedVersionMetadata:
     releaseNote: >-
       Initial release.
@@ -89,7 +89,7 @@ properties:
   modelRepositoryPath:
     type: string
     title: Bucket where models are stored. Please make sure the user/service account to create the GKE app has permission to this GCS bucket. Read Triton documentation on configs and formatting details, supporting TensorRT, TensorFlow, Pytorch, Onnx ... etc.
-    default: gs://triton_sample_models/25.05
+    default: gs://triton_sample_models/25.06
   image.ldPreloadPath:
     type: string
     title: Leave this empty by default. Triton allows users to create custom layers for backend such as TensorRT plugin or Tensorflow custom ops, the compiled shared library must be provided via LD_PRELOAD environment variable.
diff --git a/deploy/gke-marketplace-app/trt-engine/README.md b/deploy/gke-marketplace-app/trt-engine/README.md
index 01475e551c..dba63cf63e 100644
--- a/deploy/gke-marketplace-app/trt-engine/README.md
+++ b/deploy/gke-marketplace-app/trt-engine/README.md
@@ -33,7 +33,7 @@
 ```
 docker run --gpus all -it --network host \
     --shm-size=1g --ulimit memlock=-1 --ulimit stack=67108864 \
-    -v ~:/scripts nvcr.io/nvidia/tensorrt:25.05-py3
+    -v ~:/scripts nvcr.io/nvidia/tensorrt:25.06-py3
 
 pip install onnx six torch tf2onnx tensorflow
 
@@ -57,7 +57,7 @@ mkdir -p engines
 
 python3 builder.py -m models/fine-tuned/bert_tf_ckpt_large_qa_squad2_amp_128_v19.03.1/model.ckpt -o engines/bert_large_int8_bs1_s128.engine -b 1 -s 128 -c models/fine-tuned/bert_tf_ckpt_large_qa_squad2_amp_128_v19.03.1/ -v models/fine-tuned/bert_tf_ckpt_large_qa_squad2_amp_128_v19.03.1/vocab.txt --int8 --fp16 --strict --calib-num 1 -iln -imh
 
-gsutil cp bert_large_int8_bs1_s128.engine gs://triton_sample_models/25.05/bert/1/model.plan
+gsutil cp bert_large_int8_bs1_s128.engine gs://triton_sample_models/25.06/bert/1/model.plan
 ```
 
-For each Triton upgrade, container version used to generate the model, and the model path in GCS `gs://triton_sample_models/25.05/` should be updated accordingly with the correct version.
+For each Triton upgrade, container version used to generate the model, and the model path in GCS `gs://triton_sample_models/25.06/` should be updated accordingly with the correct version.
diff --git a/deploy/k8s-onprem/values.yaml b/deploy/k8s-onprem/values.yaml
index 27cb9bf33b..ac6d7a3480 100644
--- a/deploy/k8s-onprem/values.yaml
+++ b/deploy/k8s-onprem/values.yaml
@@ -30,7 +30,7 @@ tags:
   openshift: false
 
 image:
-  imageName: nvcr.io/nvidia/tritonserver:25.05-py3
+  imageName: nvcr.io/nvidia/tritonserver:25.06-py3
   pullPolicy: IfNotPresent
   modelRepositoryServer: < Replace with the IP Address of your file server >
   modelRepositoryPath: /srv/models
diff --git a/deploy/oci/values.yaml b/deploy/oci/values.yaml
index b082864f3e..be6eb13a0e 100644
--- a/deploy/oci/values.yaml
+++ b/deploy/oci/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://https://<OCI_NAMESPACE>.compat.objectstorage.<OCI_REGION>.oraclecloud.com:443/triton-inference-server-repository
   numGpus: 1
diff --git a/docs/introduction/compatibility.md b/docs/introduction/compatibility.md
index afa4ab0ac8..4332d4c8ae 100644
--- a/docs/introduction/compatibility.md
+++ b/docs/introduction/compatibility.md
@@ -38,20 +38,21 @@
 
 | Triton release version	 | NGC Tag	 | Python version	 | Torch version | TensorRT version | TensorRT-LLM version | CUDA version | CUDA Driver version | Size |
 | --- | ---  | --- | --- | --- | --- | --- | --- | --- |
+| 25.06 | nvcr.io/nvidia/tritonserver:25.06-trtllm-python-py3 | Python 3.12.3  | 2.7.0a0+79aa17489c.nv25.4 | 10.10.0.31 | 0.20.0 | 12.9.0.036 | 575.51.03 | 18.3G |
 | 25.05 | nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3 | Python 3.12.3  | 2.7.0a0+7c8ec84dab.nv25.3 | 10.9.0.34 | 0.19.0 | 12.8.1.012 | 570.124.06 | 17G |
 | 25.04 | nvcr.io/nvidia/tritonserver:25.04-trtllm-python-py3 | Python 3.12.3  | 2.7.0a0+7c8ec84dab.nv25.3 | 10.9.0.34 | 0.18.2 | 12.8.1.012 | 570.124.06 | 17G |
-| 25.03 | nvcr.io/nvidia/tritonserver:25.03-trtllm-python-py3 | Python 3.12.3  | 2.7.0a0%2B7c8ec84dab.nv25.3 | 10.9.0.34 | 0.18.0 | 12.8.1.012 | 570.124.06 | 28G |
-| 25.02 | nvcr.io/nvidia/tritonserver:25.02-trtllm-python-py3 | Python 3.12.3 | 2.6.0a0%2Becf3bae40a.nv25.1 | 10.8.0.43 | 0.17.0.post1 | 12.8.0.038 | 570.86.10 | 28G |
-| 25.01 | nvcr.io/nvidia/tritonserver:25.01-trtllm-python-py3 | Python 3.12.3  | 2.6.0a0%2Becf3bae40a.nv25.1 | 10.8.0.43 | 0.17.0 | 12.8.0.038 | 570.86.10 | 30G |
-| 24.12 | nvcr.io/nvidia/tritonserver:24.12-trtllm-python-py3 | Python 3.12.3  | 2.6.0a0%2Bdf5bbc09d1.nv24.11 | 10.7.0 | 0.16.0 | 12.6.3 | 560.35.05 | 22G |
-| 24.11 | nvcr.io/nvidia/tritonserver:24.11-trtllm-python-py3 | Python 3.10.12  | 2.5.0a0%2Be000cf0ad9.nv24.10 | 10.6.0 | 0.15.0 | 12.6.3 | 555.42.06 | 24.8G |
-| 24.10 | nvcr.io/nvidia/tritonserver:24.10-trtllm-python-py3 | Python 3.10.12  | 2.4.0a0%2B3bcc3cddb5.nv24.7 | 10.4.0 | 0.14.0 | 12.5.1.007 | 555.42.06 | 23.3G |
-| 24.09 | nvcr.io/nvidia/tritonserver:24.09-trtllm-python-py3 | Python 3.10.12  | 2.4.0a0%2B3bcc3cddb5.nv24.7 | 10.4.0 | 0.13.0 | 12.5.1.007 | 555.42.06 | 21G |
-| 24.08 | nvcr.io/nvidia/tritonserver:24.08-trtllm-python-py3 | Python 3.10.12 | 2.4.0a0%2B3bcc3cddb5.nv24.7 | 10.3.0 | 0.12.0 | 12.5.1.007 | 555.42.06 | 21G |
-| 24.07 | nvcr.io/nvidia/tritonserver:24.07-trtllm-python-py3 | Python 3.10.12 | 2.4.0a0%2B07cecf4168.nv24.5 | 10.1.0 | 0.11.0 | 12.4.1.003 | 550.54.15 | 23G |
-| 24.06 | nvcr.io/nvidia/tritonserver:24.06-trtllm-python-py3 | Python 3.10.12  | 2.3.0a0%2B40ec155e58.nv24.3 | 10.0.1 | 0.10.0 | 12.4.0.041 | 550.54.14 | 31G |
-| 24.05 | nvcr.io/nvidia/tritonserver:24.05-trtllm-python-py3 | Python 3.10.12  | 2.3.0a0%2Bebedce2 | 10.0.1.6  | 0.9.0 |  12.3.2.001 | 545.23.08 | 34G |
-| 24.04 | nvcr.io/nvidia/tritonserver:24.04-trtllm-python-py3 | Python 3.10.12  | 2.3.0a0%2Bebedce2 | 9.3.0.post12.dev1 | 0.9.0  | 12.3.2.001 | 545.23.08 | 34G |
+| 25.03 | nvcr.io/nvidia/tritonserver:25.03-trtllm-python-py3 | Python 3.12.3  | 2.7.0a0+7c8ec84dab.nv25.3 | 10.9.0.34 | 0.18.0 | 12.8.1.012 | 570.124.06 | 28G |
+| 25.02 | nvcr.io/nvidia/tritonserver:25.02-trtllm-python-py3 | Python 3.12.3 | 2.6.0a0+ecf3bae40a.nv25.1 | 10.8.0.43 | 0.17.0.post1 | 12.8.0.038 | 570.86.10 | 28G |
+| 25.01 | nvcr.io/nvidia/tritonserver:25.01-trtllm-python-py3 | Python 3.12.3  | 2.6.0a0+ecf3bae40a.nv25.1 | 10.8.0.43 | 0.17.0 | 12.8.0.038 | 570.86.10 | 30G |
+| 24.12 | nvcr.io/nvidia/tritonserver:24.12-trtllm-python-py3 | Python 3.12.3  | 2.6.0a0+df5bbc09d1.nv24.11 | 10.7.0 | 0.16.0 | 12.6.3 | 560.35.05 | 22G |
+| 24.11 | nvcr.io/nvidia/tritonserver:24.11-trtllm-python-py3 | Python 3.10.12  | 2.5.0a0+e000cf0ad9.nv24.10 | 10.6.0 | 0.15.0 | 12.6.3 | 555.42.06 | 24.8G |
+| 24.10 | nvcr.io/nvidia/tritonserver:24.10-trtllm-python-py3 | Python 3.10.12  | 2.4.0a0+3bcc3cddb5.nv24.7 | 10.4.0 | 0.14.0 | 12.5.1.007 | 555.42.06 | 23.3G |
+| 24.09 | nvcr.io/nvidia/tritonserver:24.09-trtllm-python-py3 | Python 3.10.12  | 2.4.0a0+3bcc3cddb5.nv24.7 | 10.4.0 | 0.13.0 | 12.5.1.007 | 555.42.06 | 21G |
+| 24.08 | nvcr.io/nvidia/tritonserver:24.08-trtllm-python-py3 | Python 3.10.12 | 2.4.0a0+3bcc3cddb5.nv24.7 | 10.3.0 | 0.12.0 | 12.5.1.007 | 555.42.06 | 21G |
+| 24.07 | nvcr.io/nvidia/tritonserver:24.07-trtllm-python-py3 | Python 3.10.12 | 2.4.0a0+07cecf4168.nv24.5 | 10.1.0 | 0.11.0 | 12.4.1.003 | 550.54.15 | 23G |
+| 24.06 | nvcr.io/nvidia/tritonserver:24.06-trtllm-python-py3 | Python 3.10.12  | 2.3.0a0+40ec155e58.nv24.3 | 10.0.1 | 0.10.0 | 12.4.0.041 | 550.54.14 | 31G |
+| 24.05 | nvcr.io/nvidia/tritonserver:24.05-trtllm-python-py3 | Python 3.10.12  | 2.3.0a0+ebedce2 | 10.0.1.6  | 0.9.0 |  12.3.2.001 | 545.23.08 | 34G |
+| 24.04 | nvcr.io/nvidia/tritonserver:24.04-trtllm-python-py3 | Python 3.10.12  | 2.3.0a0+ebedce2 | 9.3.0.post12.dev1 | 0.9.0  | 12.3.2.001 | 545.23.08 | 34G |
 
 ## Container Name: vllm-python-py3
 
diff --git a/docs/introduction/release_notes.md b/docs/introduction/release_notes.md
index f297ec3ac2..7038abbb01 100644
--- a/docs/introduction/release_notes.md
+++ b/docs/introduction/release_notes.md
@@ -25,9 +25,9 @@
 # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 -->
-# [Triton Inference Server Release 25.05](https://docs.nvidia.com/deeplearning/triton-inference-server/release-notes/rel-25-05.html#rel-25-05)
+# [Triton Inference Server Release 25.06](https://docs.nvidia.com/deeplearning/triton-inference-server/release-notes/rel-25-06.html#rel-25-06)
 
-The Triton Inference Server container image, release 25.05, is available
+The Triton Inference Server container image, release 25.06, is available
 on [NGC](https://ngc.nvidia.com/catalog/containers/nvidia:tritonserver) and
 is open source
 on [GitHub](https://github.com/triton-inference-server/server). Release notes can
diff --git a/python/openai/README.md b/python/openai/README.md
index 3d770caa2e..e93c9c1f16 100644
--- a/python/openai/README.md
+++ b/python/openai/README.md
@@ -51,7 +51,7 @@
 docker run -it --net=host --gpus all --rm \
   -v ${HOME}/.cache/huggingface:/root/.cache/huggingface \
   -e HF_TOKEN \
-  nvcr.io/nvidia/tritonserver:25.05-vllm-python-py3
+  nvcr.io/nvidia/tritonserver:25.06-vllm-python-py3
 ```
 
 2. Launch the OpenAI-compatible Triton Inference Server:
diff --git a/qa/L0_client_nobatch/test.sh b/qa/L0_client_nobatch/test.sh
index cb1a05d660..0c01bafb70 100755
--- a/qa/L0_client_nobatch/test.sh
+++ b/qa/L0_client_nobatch/test.sh
@@ -47,7 +47,7 @@ EXPECTED_NUM_TESTS="4"
 
 DATADIR=/data/inferenceserver/${REPO_VERSION}
 MODELDIR="${PWD}/qa_model_repository"
-rm -rf ${MODELDIR} && cp -r "${DATADIR}/qa_model_repository/onnx_*" ${MODELDIR} # Note there is a coupling in ./client_test.py
+rm -rf ${MODELDIR} && mkdir -p ${MODELDIR} && cp -r ${DATADIR}/qa_model_repository/onnx_* ${MODELDIR}/. # Note there is a coupling in ./client_test.py
 SERVER=/opt/tritonserver/bin/tritonserver
 SERVER_ARGS="--model-repository=${MODELDIR}"
 SERVER_LOG="./inference_server.log"
diff --git a/qa/L0_long_running_stress/scenarios.py b/qa/L0_long_running_stress/scenarios.py
index 650f228ab5..5b952f5b97 100755
--- a/qa/L0_long_running_stress/scenarios.py
+++ b/qa/L0_long_running_stress/scenarios.py
@@ -203,7 +203,7 @@ def __init__(
         # Add no validation models
         self.options_.append(
             PerfAnalyzerScenario.ModelOption(
-                "resnet_v1_50_def", 32, (1, 4, 1), queue_latency_range_us
+                "resnet_v1_50", 32, (1, 4, 1), queue_latency_range_us
             )
         )
         for trial in sequence_trials:
@@ -334,7 +334,7 @@ def run(self, client_metadata):
 class ResNetScenario(Scenario):
     def __init__(self, name, batch_size=32, verbose=False, out_stream=sys.stdout):
         super().__init__(name, [], verbose, out_stream)
-        self.model_name_ = "resnet_v1_50_def"
+        self.model_name_ = "resnet_v1_50"
         self.batch_size_ = batch_size
 
         img = self.preprocess("../images/vulture.jpeg")
@@ -353,7 +353,7 @@ def preprocess(self, filename):
         return scaled
 
     def postprocess(self, results):
-        output_array = results.as_numpy("resnet_v1_50/predictions/Softmax")
+        output_array = results.as_numpy("resnet_v1_50/predictions/Softmax:0")
         if len(output_array) != self.batch_size_:
             raise Exception(
                 "expected {} results, got {}".format(
@@ -377,12 +377,12 @@ def postprocess(self, results):
     def run(self, client_metadata):
         triton_client = client_metadata[0]
 
-        inputs = [grpcclient.InferInput("input", self.image_data_.shape, "FP32")]
+        inputs = [grpcclient.InferInput("input:0", self.image_data_.shape, "FP32")]
         inputs[0].set_data_from_numpy(self.image_data_)
 
         outputs = [
             grpcclient.InferRequestedOutput(
-                "resnet_v1_50/predictions/Softmax", class_count=1
+                "resnet_v1_50/predictions/Softmax:0", class_count=1
             )
         ]
         res = triton_client.infer(self.model_name_, inputs, outputs=outputs)
diff --git a/qa/L0_long_running_stress/test.sh b/qa/L0_long_running_stress/test.sh
index 1973028bcf..92d8c09b0d 100755
--- a/qa/L0_long_running_stress/test.sh
+++ b/qa/L0_long_running_stress/test.sh
@@ -130,9 +130,8 @@ cp -r ../custom_models/custom_zero_1_float32 $MODEL_DIR/custom_zero_1_float32 &&
         echo "{ key: \"execute_delay_ms\"; value: { string_value: \"10000\" }}" >> config.pbtxt && \
         echo "]" >> config.pbtxt)
 
-cp -r $DATADIR/onnx_model_store/resnet_v1_50 $MODEL_DIR/resnet_v1_50_def && \
-  (cd $MODEL_DIR/resnet_v1_50_def && \
-    sed -i 's/^name: "resnet_v1_50"/name: "resnet_v1_50_def"/' config.pbtxt && \
+cp -r $DATADIR/onnx_model_store/resnet_v1_50 $MODEL_DIR/. && \
+  (cd $MODEL_DIR/resnet_v1_50 && \
     echo "optimization { }" >> config.pbtxt)
 
 SERVER_ARGS="--model-repository=`pwd`/$MODEL_DIR"
diff --git a/qa/common/gen_jetson_trt_models b/qa/common/gen_jetson_trt_models
index 8726e7c271..b081fe9c4e 100755
--- a/qa/common/gen_jetson_trt_models
+++ b/qa/common/gen_jetson_trt_models
@@ -34,7 +34,7 @@
 # Make all generated files accessible outside of container
 umask 0000
 # Set the version of the models
-TRITON_VERSION=${TRITON_VERSION:=25.05}
+TRITON_VERSION=${TRITON_VERSION:=25.06}
 # Set the CUDA device to use
 CUDA_DEVICE=${RUNNER_ID:=0}
 # Set TensorRT image
diff --git a/qa/common/gen_qa_custom_ops b/qa/common/gen_qa_custom_ops
index 96801e4470..108b1daa53 100755
--- a/qa/common/gen_qa_custom_ops
+++ b/qa/common/gen_qa_custom_ops
@@ -37,7 +37,7 @@
 ##
 ############################################################################
 
-TRITON_VERSION=${TRITON_VERSION:=25.05}
+TRITON_VERSION=${TRITON_VERSION:=25.06}
 NVIDIA_UPSTREAM_VERSION=${NVIDIA_UPSTREAM_VERSION:=$TRITON_VERSION}
 PYTORCH_IMAGE=${PYTORCH_IMAGE:=nvcr.io/nvidia/pytorch:$NVIDIA_UPSTREAM_VERSION-py3}
 UBUNTU_IMAGE=${UBUNTU_IMAGE:=ubuntu:24.04}
diff --git a/qa/common/gen_qa_model_repository b/qa/common/gen_qa_model_repository
index 7f4741d1c7..2deeb97da5 100755
--- a/qa/common/gen_qa_model_repository
+++ b/qa/common/gen_qa_model_repository
@@ -48,7 +48,7 @@
 ##
 ############################################################################
 
-TRITON_VERSION=${TRITON_VERSION:=25.05}
+TRITON_VERSION=${TRITON_VERSION:=25.06}
 
 # ONNX. Use ONNX_OPSET 0 to use the default for ONNX version
 ONNX_VERSION=1.16.1