Merge branch 'main' into kprashanth-tritonfrontend-rfeatures

CMakeLists.txt

@@ -221,7 +221,7 @@ ExternalProject_Add(triton-server
     -Dre2_DIR:PATH=${TRITON_THIRD_PARTY_INSTALL_PREFIX}/re2/${LIB_DIR}/cmake/re2
     -Dabsl_DIR:PATH=${TRITON_THIRD_PARTY_INSTALL_PREFIX}/absl/${LIB_DIR}/cmake/absl
     -DCURL_DIR:STRING=${TRITON_THIRD_PARTY_INSTALL_PREFIX}/curl/${LIB_DIR}/cmake/CURL
-    -Dnlohmann_json_DIR:PATH=${TRITON_THIRD_PARTY_INSTALL_PREFIX}/nlohmann_json/${LIB_DIR}/cmake/nlohmann_json
+    -Dnlohmann_json_DIR:PATH=${TRITON_THIRD_PARTY_INSTALL_PREFIX}/nlohmann_json/share/cmake/nlohmann_json
     -DLibevent_DIR:PATH=${TRITON_THIRD_PARTY_INSTALL_PREFIX}/libevent/lib/cmake/libevent
     -Dlibevhtp_DIR:PATH=${TRITON_THIRD_PARTY_INSTALL_PREFIX}/libevhtp/lib/cmake/libevhtp
     -Dstorage_client_DIR:PATH=${TRITON_THIRD_PARTY_INSTALL_PREFIX}/google-cloud-cpp/${LIB_DIR}/cmake/storage_client

Dockerfile.QA

@@ -59,20 +59,19 @@ RUN apt-get update && \
             libboost-dev \
             python3-dev \
             python3-pip \
+            python3-wheel \
+            python3-setuptools \
             rapidjson-dev \
             software-properties-common && \
     rm -rf /var/lib/apt/lists/*
 
-RUN pip3 install --upgrade pip && \
-    pip3 install --upgrade wheel setuptools
-
 RUN apt update -q=2 \
     && apt install -y gpg wget \
     && wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc 2>/dev/null | gpg --dearmor - |  tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null \
     && . /etc/os-release \
     && echo "deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ $UBUNTU_CODENAME main" | tee /etc/apt/sources.list.d/kitware.list >/dev/null \
     && apt-get update -q=2 \
-    && apt-get install -y --no-install-recommends cmake=3.27.7* cmake-data=3.27.7*
+    && apt-get install -y --no-install-recommends cmake=3.28.3* cmake-data=3.28.3*
 
 # Add inception_graphdef model to example repo
 WORKDIR /workspace/docs/examples/model_repository
@@ -311,20 +310,12 @@ ARG TARGETPLATFORM
 ENV DEBIAN_FRONTEND=noninteractive
 
 # install platform specific packages
-RUN if [ $(cat /etc/os-release | grep 'VERSION_ID="20.04"' | wc -l) -ne 0 ]; then \
-        apt-get update && \
-        apt-get install -y --no-install-recommends \
-                libpng-dev; \
-    elif [ $(cat /etc/os-release | grep 'VERSION_ID="22.04"' | wc -l) -ne 0 ]; then \
-        apt-get update && \
-        apt-get install -y --no-install-recommends \
-                libpng-dev; \
-    elif [ $(cat /etc/os-release | grep 'VERSION_ID="18.04"' | wc -l) -ne 0 ]; then \
+RUN if grep -qE '^VERSION_ID="(18\.04|20\.04|22\.04|24\.04)' /etc/os-release; then \
         apt-get update && \
         apt-get install -y --no-install-recommends \
                 libpng-dev; \
     else \
-        echo "Ubuntu version must be either 18.04, 20.04 or 22.04" && \
+        echo "Ubuntu version must be either 18.04, 20.04, 22.04 or 24.04" && \
         exit 1; \
     fi
 
@@ -337,14 +328,14 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
                               libarchive-dev \
                               libopencv-core-dev \
                               libzmq3-dev \
-                              maven \
                               openjdk-11-jdk \
                               nginx \
                               npm \
                               protobuf-compiler \
                               python3-dev \
                               python3-pip \
                               python3-protobuf \
+                              python3-wheel \
                               python3-setuptools \
                               swig \
                               valgrind && \
@@ -354,9 +345,8 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 RUN rm -f /usr/bin/python && \
     ln -s /usr/bin/python3 /usr/bin/python
 
-RUN pip3 install --upgrade wheel setuptools && \
-    pip3 install --upgrade "numpy<2" pillow attrdict future grpcio requests gsutil \
-                           awscli six grpcio-channelz prettytable virtualenv \
+RUN pip3 install --upgrade "numpy<2" pillow attrdict future "grpcio<1.68" requests gsutil \
+                           awscli six "grpcio-channelz<1.68" prettytable virtualenv \
                            check-jsonschema
 
 # go needed for example go client test.

Dockerfile.sdk

@@ -29,7 +29,7 @@
 #
 
 # Base image on the minimum Triton container
-ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.10-py3-min
+ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.11-py3-min
 
 ARG TRITON_CLIENT_REPO_SUBDIR=clientrepo
 ARG TRITON_PA_REPO_SUBDIR=perfanalyzerrepo
@@ -44,7 +44,7 @@ ARG JAVA_BINDINGS_MAVEN_VERSION=3.8.4
 ARG JAVA_BINDINGS_JAVACPP_PRESETS_TAG=1.5.8
 
 # DCGM version to install for Model Analyzer
-ARG DCGM_VERSION=3.2.6
+ARG DCGM_VERSION=3.3.6
 
 ARG NVIDIA_TRITON_SERVER_SDK_VERSION=unknown
 ARG NVIDIA_BUILD_ID=unknown
@@ -57,6 +57,7 @@ FROM ${BASE_IMAGE} AS sdk_build
 
 # Ensure apt-get won't prompt for selecting options
 ENV DEBIAN_FRONTEND=noninteractive
+ENV PIP_BREAK_SYSTEM_PACKAGES=1
 
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
@@ -78,15 +79,15 @@ RUN apt-get update && \
             python3 \
             python3-pip \
             python3-dev \
+            python3-wheel \
+            python3-setuptools \
             rapidjson-dev \
             vim \
             wget \
             python3-pdfkit \
             openjdk-11-jdk \
             maven && \
-    pip3 install --upgrade wheel setuptools && \
-    pip3 install --upgrade grpcio-tools && \
-    pip3 install --upgrade pip
+    pip3 install --upgrade "grpcio-tools<1.68"
 
 # Client build requires recent version of CMake (FetchContent required)
 # Using CMAKE installation instruction from:: https://apt.kitware.com/
@@ -96,7 +97,7 @@ RUN apt update -q=2 \
     && . /etc/os-release \
     && echo "deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ $UBUNTU_CODENAME main" | tee /etc/apt/sources.list.d/kitware.list >/dev/null \
     && apt-get update -q=2 \
-    && apt-get install -y --no-install-recommends cmake=3.27.7* cmake-data=3.27.7* \
+    && apt-get install -y --no-install-recommends cmake=3.28.3* cmake-data=3.28.3* \
     && cmake --version
 
 # Build expects "python" executable (not python3).
@@ -183,6 +184,7 @@ FROM ${BASE_IMAGE}
 
 # Ensure apt-get won't prompt for selecting options
 ENV DEBIAN_FRONTEND=noninteractive
+ENV PIP_BREAK_SYSTEM_PACKAGES=1
 
 ARG DCGM_VERSION
 ARG TRITON_REPO_ORGANIZATION
@@ -205,14 +207,14 @@ RUN apt-get update && \
             python3 \
             python3-pip \
             python3-dev \
+            python3-wheel \
+            python3-setuptools \
             vim \
             wget \
             python3-pdfkit \
             maven \
             default-jdk && \
-    pip3 install --upgrade wheel setuptools && \
-    pip3 install --upgrade grpcio-tools && \
-    pip3 install --upgrade pip
+    pip3 install "grpcio<1.68" "grpcio-tools<1.68"
 
 WORKDIR /workspace
 COPY TRITON_VERSION .
@@ -250,7 +252,7 @@ RUN pip3 install install/python/genai_perf-*.whl
 RUN if [ "$TRITON_ENABLE_GPU" = "ON" ]; then \
         [ "$(uname -m)" != "x86_64" ] && arch="sbsa" || arch="x86_64" && \
         curl -o /tmp/cuda-keyring.deb \
-        https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/$arch/cuda-keyring_1.0-1_all.deb \
+        https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/$arch/cuda-keyring_1.1-1_all.deb \
         && apt install /tmp/cuda-keyring.deb && rm /tmp/cuda-keyring.deb && \
         apt-get update && apt-get install -y datacenter-gpu-manager=1:${DCGM_VERSION}; \
     fi

README.md

@@ -32,8 +32,8 @@
 
 >[!WARNING]
 >You are currently on the `main` branch which tracks under-development progress
->towards the next release. The current release is version [2.51.0](https://github.com/triton-inference-server/server/releases/latest)
->and corresponds to the 24.10 container release on NVIDIA GPU Cloud (NGC).
+>towards the next release. The current release is version [2.52.0](https://github.com/triton-inference-server/server/releases/latest)
+>and corresponds to the 24.11 container release on NVIDIA GPU Cloud (NGC).
 
 Triton Inference Server is an open source inference serving software that
 streamlines AI inferencing. Triton enables teams to deploy any AI model from
@@ -91,16 +91,16 @@ Inference Server with the
 
 ```bash
 # Step 1: Create the example model repository
-git clone -b r24.10 https://github.com/triton-inference-server/server.git
+git clone -b r24.11 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:24.10-py3 tritonserver --model-repository=/models
+docker run --gpus=1 --rm --net=host -v ${PWD}/model_repository:/models nvcr.io/nvidia/tritonserver:24.11-py3 tritonserver --model-repository=/models
 
 # 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:24.10-py3-sdk
+docker run -it --rm --net=host nvcr.io/nvidia/tritonserver:24.11-py3-sdk
 /workspace/install/bin/image_client -m densenet_onnx -c 3 -s INCEPTION /workspace/images/mug.jpg
 
 # Inference should return the following

TRITON_VERSION

@@ -1 +1 @@
-2.53.0dev
+2.53.0dev