Merge branch 'main' of https://github.com/triton-inference-server/server into spolisetty_pb_model_load

Author: pskiran1

Dockerfile.sdk

@@ -29,7 +29,7 @@
 #
 
 # Base image on the minimum Triton container
-ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:25.06-py3-min
+ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:25.07-py3-min
 
 ARG TRITON_CLIENT_REPO_SUBDIR=clientrepo
 ARG TRITON_PA_REPO_SUBDIR=perfanalyzerrepo
@@ -60,34 +60,36 @@ ENV PIP_BREAK_SYSTEM_PACKAGES=1 CMAKE_POLICY_VERSION_MINIMUM=3.5
 
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
-            ca-certificates \
-            software-properties-common \
             autoconf \
             automake \
             build-essential \
+            ca-certificates \
             curl \
             git \
             gperf \
             libb64-dev \
             libgoogle-perftools-dev \
-            libopencv-dev \
             libopencv-core-dev \
+            libopencv-dev \
             libssl-dev \
             libtool \
+            maven \
+            openjdk-11-jdk \
             pkg-config \
             python3 \
-            python3-pip \
             python3-dev \
-            python3-wheel \
+            python3-pdfkit \
+            python3-pip \
             python3-setuptools \
+            python3-wheel \
             rapidjson-dev \
+            software-properties-common \
             vim \
-            wget \
-            python3-pdfkit \
-            openjdk-11-jdk \
-            maven && \
+            wget && \
     pip3 install --upgrade "grpcio-tools<1.68" cmake==4.0.3
 
+ENV CMAKE_POLICY_MINIMUM_REQUIRED=3.5
+
 # Build expects "python" executable (not python3).
 RUN rm -f /usr/bin/python && \
     ln -s /usr/bin/python3 /usr/bin/python
@@ -126,8 +128,7 @@ RUN cmake -DCMAKE_INSTALL_PREFIX=/workspace/install \
           -DTRITON_ENABLE_JAVA_HTTP=ON \
           -DTRITON_ENABLE_EXAMPLES=ON -DTRITON_ENABLE_TESTS=ON \
           -DTRITON_ENABLE_GPU=${TRITON_ENABLE_GPU} /workspace/client
-RUN make -j16 cc-clients java-clients && \
-    rm -fr ~/.m2
+RUN cmake --build . -v --parallel --target cc-clients java-clients
 
 # TODO: PA will rebuild the CC clients since it depends on it.
 # This should be optimized so that we do not have to build
@@ -145,6 +146,7 @@ RUN if [ "$TRITON_PERF_ANALYZER_BUILD" = "1" ]; then \
           -DTRITON_COMMON_REPO_TAG=${TRITON_COMMON_REPO_TAG} \
           -DTRITON_CORE_REPO_TAG=${TRITON_CORE_REPO_TAG} \
           -DTRITON_CLIENT_REPO_TAG=${TRITON_CLIENT_REPO_TAG} \
+          -DTRITON_THIRD_PARTY_REPO_TAG=${TRITON_THIRD_PARTY_REPO_TAG} \
           -DTRITON_ENABLE_PERF_ANALYZER_C_API=ON \
           -DTRITON_ENABLE_PERF_ANALYZER_TFS=ON \
           -DTRITON_ENABLE_PERF_ANALYZER_TS=ON \
@@ -156,7 +158,7 @@ RUN if [ "$TRITON_PERF_ANALYZER_BUILD" = "1" ]; then \
           -DTRITON_PACKAGE_PERF_ANALYZER=ON \
           -DTRITON_ENABLE_GPU=${TRITON_ENABLE_GPU} \
         /workspace/perf_analyzer && \
-        make -j16 perf-analyzer python-clients && \
+        cmake --build . -v --parallel --target perf-analyzer python-clients && \
         pip3 install build && \
         cd /workspace/perf_analyzer/genai-perf && \
         python3 -m build --wheel --outdir /workspace/install/python; \
@@ -169,12 +171,13 @@ RUN if [ "$TRITON_PERF_ANALYZER_BUILD" = "1" ]; then \
           -DTRITON_REPO_ORGANIZATION=${TRITON_REPO_ORGANIZATION} \
           -DTRITON_COMMON_REPO_TAG=${TRITON_COMMON_REPO_TAG} \
           -DTRITON_CLIENT_REPO_TAG=${TRITON_CLIENT_REPO_TAG} \
+          -DTRITON_THIRD_PARTY_REPO_TAG=${TRITON_THIRD_PARTY_REPO_TAG} \
           -DTRITON_ENABLE_PYTHON_HTTP=ON \
           -DTRITON_ENABLE_PYTHON_GRPC=ON \
           -DTRITON_PACKAGE_PERF_ANALYZER=ON \
           -DTRITON_ENABLE_GPU=${TRITON_ENABLE_GPU} \
         /workspace/perf_analyzer && \
-        make -j16 python-clients && \
+        cmake --build . -v --parallel --target python-clients && \
         mkdir -p /workspace/install/python && \
         cp /workspace/perf_analyzer/genai_perf-*.whl /workspace/install/python/; \
     fi
@@ -205,26 +208,27 @@ ARG TRITON_ENABLE_GPU
 
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
-            software-properties-common \
             curl \
+            default-jdk \
             git \
             gperf \
             libb64-dev \
             libgoogle-perftools-dev \
-            libopencv-dev \
             libopencv-core-dev \
+            libopencv-dev \
             libssl-dev \
             libtool \
+            maven \
+            perl \
             python3 \
-            python3-pip \
             python3-dev \
-            python3-wheel \
+            python3-pdfkit \
+            python3-pip \
             python3-setuptools \
+            python3-wheel \
+            software-properties-common \
             vim \
-            wget \
-            python3-pdfkit \
-            maven \
-            default-jdk && \
+            wget && \
     pip3 install "grpcio<1.68" "grpcio-tools<1.68"
 
 WORKDIR /workspace
@@ -265,7 +269,10 @@ RUN if [ "$TRITON_ENABLE_GPU" = "ON" ]; then \
         curl -o /tmp/cuda-keyring.deb \
         https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/$arch/cuda-keyring_1.1-1_all.deb \
         && apt install /tmp/cuda-keyring.deb && rm /tmp/cuda-keyring.deb && \
-        apt update && apt install --yes datacenter-gpu-manager-4-dev=1:${DCGM_VERSION}; \
+        apt update && \
+        apt install --yes --no-install-recommends \
+               datacenter-gpu-manager-4-core=1:${DCGM_VERSION} \
+               datacenter-gpu-manager-4-dev=1:${DCGM_VERSION}; \
     fi
 
 # Build expects "python" executable (not python3).

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 [2.59.0](https://github.com/triton-inference-server/server/releases/latest)
->and corresponds to the 25.06 container release on NVIDIA GPU Cloud (NGC).
+>towards the next release. The current release is version [2.59.1](https://github.com/triton-inference-server/server/releases/latest)
+>and corresponds to the 25.07 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 r25.06 https://github.com/triton-inference-server/server.git
+git clone -b r25.07 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:25.06-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:25.07-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:25.06-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:25.07-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

@@ -72,8 +72,8 @@
 
 DEFAULT_TRITON_VERSION_MAP = {
     "release_version": "2.60.0dev",
-    "triton_container_version": "25.07dev",
-    "upstream_container_version": "25.06",
+    "triton_container_version": "25.08dev",
+    "upstream_container_version": "25.07",
     "ort_version": "1.22.0",
     "ort_openvino_version": "2025.2.0",
     "standalone_openvino_version": "2025.2.0",
@@ -858,19 +858,23 @@ def install_dcgm_libraries(dcgm_version, target_machine):
 # Install DCGM. Steps from https://developer.nvidia.com/dcgm#Downloads
 RUN dnf config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/rhel8/sbsa/cuda-rhel8.repo \\
     && dnf clean expire-cache \\
-    && dnf install --assumeyes datacenter-gpu-manager-4-devel=1:{}
+    && dnf install --assumeyes \\
+                 datacenter-gpu-manager-4-core=1:{} \\
+                 datacenter-gpu-manager-4-devel=1:{}
 """.format(
-                    dcgm_version, dcgm_version
+                    dcgm_version, dcgm_version, dcgm_version
                 )
             else:
                 return """
 ENV DCGM_VERSION {}
 # Install DCGM. Steps from https://developer.nvidia.com/dcgm#Downloads
 RUN dnf config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/rhel8/x86_64/cuda-rhel8.repo \\
     && dnf clean expire-cache \\
-    && dnf install --assumeyes datacenter-gpu-manager-4-devel=1:{}
+    && dnf install --assumeyes \\
+                 datacenter-gpu-manager-4-core=1:{} \\
+                 datacenter-gpu-manager-4-devel=1:{}
 """.format(
-                    dcgm_version, dcgm_version
+                    dcgm_version, dcgm_version, dcgm_version
                 )
         else:
             if target_machine == "aarch64":
@@ -882,9 +886,11 @@ def install_dcgm_libraries(dcgm_version, target_machine):
       && apt install /tmp/cuda-keyring.deb \\
       && rm /tmp/cuda-keyring.deb \\
       && apt update \\
-      && apt install --yes datacenter-gpu-manager-4-dev=1:{}
+      && apt install --yes --no-install-recommends \\
+                  datacenter-gpu-manager-4-core=1:{} \\
+                  datacenter-gpu-manager-4-dev=1:{}
 """.format(
-                    dcgm_version, dcgm_version
+                    dcgm_version, dcgm_version, dcgm_version
                 )
             else:
                 return """
@@ -895,9 +901,11 @@ def install_dcgm_libraries(dcgm_version, target_machine):
       && apt install /tmp/cuda-keyring.deb \\
       && rm /tmp/cuda-keyring.deb \\
       && apt update \\
-      && apt install --yes datacenter-gpu-manager-4-dev=1:{}
+      && apt install --yes --no-install-recommends \\
+                   datacenter-gpu-manager-4-core=1:{} \\
+                   datacenter-gpu-manager-4-dev=1:{}
 """.format(
-                    dcgm_version, dcgm_version
+                    dcgm_version, dcgm_version, dcgm_version
                 )
 
 

deploy/aws/values.yaml

@@ -27,7 +27,7 @@
 replicaCount: 1
 
 image:
-  imageName: nvcr.io/nvidia/tritonserver:25.06-py3
+  imageName: nvcr.io/nvidia/tritonserver:25.07-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: "2.59.0"
+appVersion: "2.59.1"
 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:25.06-py3
+  imageName: nvcr.io/nvidia/tritonserver:25.07-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/r25.06/docs/user_guide/model_management.md
+    # See https://github.com/triton-inference-server/server/blob/r25.07/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/r25.06/README.md
+    # see https://github.com/triton-inference-server/server/blob/r25.07/README.md
     #  for more details
 
 service:

deploy/gcp/values.yaml

@@ -27,7 +27,7 @@
 replicaCount: 1
 
 image:
-  imageName: nvcr.io/nvidia/tritonserver:25.06-py3
+  imageName: nvcr.io/nvidia/tritonserver:25.07-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:25.06-py3-sdk
+  - image: nvcr.io/nvidia/tritonserver:25.07-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=2.59
-export MINOR_VERSION=2.59.0
-export NGC_VERSION=25.06-py3
+export MINOR_VERSION=2.59.1
+export NGC_VERSION=25.07-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: "2.59"
 description: Triton Inference Server
 name: triton-inference-server
-version: 2.59.0
+version: 2.59.1