Update versions

Author: nv-kmcgill53

Dockerfile.sdk

@@ -29,7 +29,7 @@
 #
 
 # Base image on the minimum Triton container
-ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:25.01-py3-min
+ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:25.02-py3-min
 
 ARG TRITON_CLIENT_REPO_SUBDIR=clientrepo
 ARG TRITON_PA_REPO_SUBDIR=perfanalyzerrepo

TRITON_VERSION

@@ -1 +1 @@
-2.55.0dev
+2.55.0

deploy/aws/values.yaml

@@ -27,7 +27,7 @@
 replicaCount: 1
 
 image:
-  imageName: nvcr.io/nvidia/tritonserver:25.01-py3
+  imageName: nvcr.io/nvidia/tritonserver:25.02-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: "2.54.0"
+appVersion: "2.55.0"
 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:25.01-py3
+  imageName: nvcr.io/nvidia/tritonserver:25.02-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/r25.01/docs/model_management.md
+    # See https://github.com/triton-inference-server/server/blob/r25.02/docs/model_management.md
     #  for more details
     #- --model-control-mode=explicit|poll|none
     #
     # Additional server args
     #
-    # see https://github.com/triton-inference-server/server/blob/r25.01/README.md
+    # see https://github.com/triton-inference-server/server/blob/r25.02/README.md
     #  for more details
 
 service:

deploy/gcp/values.yaml

@@ -27,7 +27,7 @@
 replicaCount: 1
 
 image:
-  imageName: nvcr.io/nvidia/tritonserver:25.01-py3
+  imageName: nvcr.io/nvidia/tritonserver:25.02-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:25.01-py3-sdk
+  - image: nvcr.io/nvidia/tritonserver:25.02-py3-sdk
     imagePullPolicy: Always
     name: nv-triton-client
     securityContext:

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

@@ -28,8 +28,8 @@
 export REGISTRY=gcr.io/$(gcloud config get-value project | tr ':' '/')
 export APP_NAME=tritonserver
 export MAJOR_VERSION=2.53
-export MINOR_VERSION=2.54.0
-export NGC_VERSION=25.01-py3
+export MINOR_VERSION=2.55.0
+export NGC_VERSION=25.02-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: "2.53"
 description: Triton Inference Server
 name: triton-inference-server
-version: 2.54.0
+version: 2.55.0

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/25.01
-publishedVersion: '2.54.0'
+modelRepositoryPath: gs://triton_sample_models/25.02
+publishedVersion: '2.55.0'
 gcpMarketplace: true
 
 image:
   registry: gcr.io
   repository: nvidia-ngc-public/tritonserver
-  tag: 25.01-py3
+  tag: 25.02-py3
   pullPolicy: IfNotPresent
   # modify the model repository here to match your GCP storage bucket
   numGpus: 1

deploy/gke-marketplace-app/server-deployer/data-test/schema.yaml

@@ -27,7 +27,7 @@
 x-google-marketplace:
   schemaVersion: v2
   applicationApiVersion: v1beta1
-  publishedVersion: '2.54.0'
+  publishedVersion: '2.55.0'
   publishedVersionMetadata:
     releaseNote: >-
       Initial release.

deploy/gke-marketplace-app/server-deployer/schema.yaml

@@ -27,7 +27,7 @@
 x-google-marketplace:
   schemaVersion: v2
   applicationApiVersion: v1beta1
-  publishedVersion: '2.54.0'
+  publishedVersion: '2.55.0'
   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/25.01
+    default: gs://triton_sample_models/25.02
   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.

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:25.01-py3
+    -v ~:/scripts nvcr.io/nvidia/tensorrt:25.02-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/25.01/bert/1/model.plan
+gsutil cp bert_large_int8_bs1_s128.engine gs://triton_sample_models/25.02/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/25.01/` 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/25.02/` should be updated accordingly with the correct version.

deploy/k8s-onprem/values.yaml

@@ -29,7 +29,7 @@ tags:
   loadBalancing: true
 
 image:
-  imageName: nvcr.io/nvidia/tritonserver:25.01-py3
+  imageName: nvcr.io/nvidia/tritonserver:25.02-py3
   pullPolicy: IfNotPresent
   modelRepositoryServer: < Replace with the IP Address of your file server >
   modelRepositoryPath: /srv/models

deploy/oci/values.yaml

@@ -27,7 +27,7 @@
 replicaCount: 1
 
 image:
-  imageName: nvcr.io/nvidia/tritonserver:25.01-py3
+  imageName: nvcr.io/nvidia/tritonserver:25.02-py3
   pullPolicy: IfNotPresent
   modelRepositoryPath: s3://https://<OCI_NAMESPACE>.compat.objectstorage.<OCI_REGION>.oraclecloud.com:443/triton-inference-server-repository
   numGpus: 1

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:25.01-vllm-python-py3
+  nvcr.io/nvidia/tritonserver:25.02-vllm-python-py3
 ```
 
 2. Launch the OpenAI-compatible Triton Inference Server:

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=${TRITON_VERSION:=25.01}
+TRITON_VERSION=${TRITON_VERSION:=25.02}
 # Set the CUDA device to use
 CUDA_DEVICE=${RUNNER_ID:=0}
 # Set TensorRT image

qa/common/gen_qa_custom_ops

@@ -37,7 +37,7 @@
 ##
 ############################################################################
 
-TRITON_VERSION=${TRITON_VERSION:=25.01}
+TRITON_VERSION=${TRITON_VERSION:=25.02}
 NVIDIA_UPSTREAM_VERSION=${NVIDIA_UPSTREAM_VERSION:=$TRITON_VERSION}
 TENSORFLOW_IMAGE=${TENSORFLOW_IMAGE:=nvcr.io/nvidia/tensorflow:$NVIDIA_UPSTREAM_VERSION-tf2-py3}
 PYTORCH_IMAGE=${PYTORCH_IMAGE:=nvcr.io/nvidia/pytorch:$NVIDIA_UPSTREAM_VERSION-py3}

qa/common/gen_qa_model_repository

@@ -48,7 +48,7 @@
 ##
 ############################################################################
 
-TRITON_VERSION=${TRITON_VERSION:=25.01}
+TRITON_VERSION=${TRITON_VERSION:=25.02}
 
 # ONNX. Use ONNX_OPSET 0 to use the default for ONNX version
 ONNX_VERSION=1.16.1