Update main post-23.05 release (#5880)

* Update README and versions for 23.05 branch * Changes to support 23.05 (#5782) * Update python and conda version * Update CMAKE installation * Update checksum version * Update ubuntu base image to 22.04 * Use ORT 1.15.0 * Set CMAKE to pull latest version * Update libre package version * Removing unused argument * Adding condition for ubuntu 22.04 * Removing installation of the package from the devel container * Nnshah1 u22.04 (#5770) * Update CMAKE installation * Update python and conda version * Update CMAKE installation * Update checksum version * Update ubuntu base image to 22.04 * updating versions for ubuntu 22.04 * remove re2 --------- Co-authored-by: Neelay Shah <neelays@neelays-dt.nvidia.com> Co-authored-by: Neelay Shah <neelays@nvidia.com> * Set ONNX version to 1.13.0 * Fix L0_custom_ops for ubuntu 22.04 (#5775) * add back rapidjson-dev --------- Co-authored-by: Neelay Shah <neelays@neelays-dt.nvidia.com> Co-authored-by: Neelay Shah <neelays@nvidia.com> Co-authored-by: nv-kmcgill53 <101670481+nv-kmcgill53@users.noreply.github.com> * Fix L0_mlflow (#5805) * working thread * remove default install of blinker * merge issue fixed * Fix L0_backend_python/env test (#5799) * Fix L0_backend_python/env test * Address comment * Update the copyright * Fix up * Fix L0_http_fuzz (#5776) * installing python 3.8.16 for test * spelling Co-authored-by: Neelay Shah <neelays@nvidia.com> * use util functions to install python3.8 in an easier way --------- Co-authored-by: Neelay Shah <neelays@nvidia.com> * Update Windows versions for 23.05 release (#5826) * Rename Ubuntu 20.04 mentions to 22.04 (#5849) * Update DCGM version (#5856) * Update DCGM version (#5857) * downgrade DCGM version to 2.4.7 (#5860) * Updating link for latest release notes to 23.05 --------- Co-authored-by: Neelay Shah <neelays@neelays-dt.nvidia.com> Co-authored-by: Neelay Shah <neelays@nvidia.com> Co-authored-by: nv-kmcgill53 <101670481+nv-kmcgill53@users.noreply.github.com> Co-authored-by: Iman Tabrizian <iman.tabrizian@gmail.com>
triton-inference-server · Jun 1, 2023 · e0e2c1a · e0e2c1a
1 parent b9e8125
commit e0e2c1a
Show file tree

Hide file tree

Showing 39 changed files with 235 additions and 199 deletions.
diff --git a/Dockerfile.QA b/Dockerfile.QA
@@ -62,13 +62,15 @@ RUN apt-get update && \
 RUN pip3 install --upgrade pip && \
     pip3 install --upgrade wheel setuptools
 
-RUN wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc 2>/dev/null | \
-      gpg --dearmor - |  \
-      tee /etc/apt/trusted.gpg.d/kitware.gpg >/dev/null && \
-    apt-add-repository 'deb https://apt.kitware.com/ubuntu/ focal main' && \
+RUN apt update && 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 && \
-    apt-get install -y --no-install-recommends \
-      cmake-data=3.25.2-0kitware1ubuntu20.04.1 cmake=3.25.2-0kitware1ubuntu20.04.1
+    apt-get install -y --no-install-recommends cmake cmake-data 
 
 # Add inception_graphdef model to example repo
 WORKDIR /workspace/docs/examples/model_repository
@@ -294,12 +296,16 @@ RUN if [ $(cat /etc/os-release | grep 'VERSION_ID="20.04"' | wc -l) -ne 0 ]; the
         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 \
         apt-get update && \
         apt-get install -y --no-install-recommends \
                 libpng-dev; \
     else \
-        echo "Ubuntu version must be either 18.04 or 20.04" && \
+        echo "Ubuntu version must be either 18.04, 20.04 or 22.04" && \
         exit 1; \
     fi
 
@@ -333,11 +339,6 @@ RUN pip3 install --upgrade wheel setuptools && \
     pip3 install --upgrade numpy pillow attrdict future grpcio requests gsutil \
                            awscli six grpcio-channelz prettytable virtualenv
 
-# L0_http_fuzz is hitting similar issue with boofuzz with latest version (0.4.0):
-# https://github.com/jtpereyda/boofuzz/issues/529
-# Hence, fixing the boofuzz version to 0.3.0
-RUN pip3 install 'boofuzz==0.3.0'
-
 # go needed for example go client test.
 RUN if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
       wget https://golang.org/dl/go1.19.1.linux-arm64.tar.gz && \

diff --git a/Dockerfile.sdk b/Dockerfile.sdk
@@ -29,21 +29,20 @@
 #
 
 # Base image on the minimum Triton container
-ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:23.04-py3-min
+ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:23.05-py3-min
 
 ARG TRITON_CLIENT_REPO_SUBDIR=clientrepo
 ARG TRITON_COMMON_REPO_TAG=main
 ARG TRITON_CORE_REPO_TAG=main
 ARG TRITON_BACKEND_REPO_TAG=main
 ARG TRITON_THIRD_PARTY_REPO_TAG=main
 ARG TRITON_MODEL_ANALYZER_REPO_TAG=main
-ARG CMAKE_UBUNTU_VERSION=20.04
 ARG TRITON_ENABLE_GPU=ON
 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=2.2.9
+ARG DCGM_VERSION=2.4.7
 
 ARG NVIDIA_TRITON_SERVER_SDK_VERSION=unknown
 ARG NVIDIA_BUILD_ID=unknown
@@ -87,25 +86,18 @@ RUN apt-get update && \
     pip3 install --upgrade grpcio-tools && \
     pip3 install --upgrade pip
 
-ARG CMAKE_UBUNTU_VERSION
 # Client build requires recent version of CMake (FetchContent required)
-RUN wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc 2>/dev/null | \
-      gpg --dearmor - |  \
-      tee /etc/apt/trusted.gpg.d/kitware.gpg >/dev/null && \
-    if [ "$CMAKE_UBUNTU_VERSION" = "20.04" ]; then \
-      apt-add-repository 'deb https://apt.kitware.com/ubuntu/ focal main' && \
-      apt-get update && \
-      apt-get install -y --no-install-recommends \
-        cmake-data=3.25.2-0kitware1ubuntu20.04.1 cmake=3.25.2-0kitware1ubuntu20.04.1; \
-    elif [ "$CMAKE_UBUNTU_VERSION" = "18.04" ]; then \
-      apt-add-repository 'deb https://apt.kitware.com/ubuntu/ bionic main' && \
-      apt-get update && \
-      apt-get install -y --no-install-recommends \
-        cmake-data=3.18.4-0kitware1 cmake=3.18.4-0kitware1; \
-    else \
-      echo "ERROR: Only support CMAKE_UBUNTU_VERSION to be 18.04 or 20.04" && false; \
-    fi && \
-    cmake --version
+# Using CMAKE installation instruction from:: https://apt.kitware.com/
+RUN apt update && 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 && \
+    apt-get install -y --no-install-recommends cmake cmake-data && \
+    cmake --version 
 
 # Build expects "python" executable (not python3).
 RUN rm -f /usr/bin/python && \
@@ -224,7 +216,7 @@ RUN pip3 install --upgrade numpy pillow attrdict && \
 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/ubuntu2004/$arch/cuda-keyring_1.0-1_all.deb \
+        https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/$arch/cuda-keyring_1.0-1_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

diff --git a/Dockerfile.win10.min b/Dockerfile.win10.min
@@ -71,7 +71,7 @@ WORKDIR /
 #
 # Installing Vcpkg
 #
-ARG VCPGK_VERSION=2023.02.24
+ARG VCPGK_VERSION=2022.11.14
 RUN git clone --single-branch --depth=1 -b %VCPGK_VERSION% https://github.com/microsoft/vcpkg.git
 WORKDIR /vcpkg
 RUN bootstrap-vcpkg.bat
@@ -103,9 +103,9 @@ LABEL CMAKE_VERSION=${CMAKE_VERSION}
 #
 # Installing CUDA
 #
-ARG CUDA_MAJOR=11
-ARG CUDA_MINOR=8
-ARG CUDA_PATCH=0
+ARG CUDA_MAJOR=12
+ARG CUDA_MINOR=1
+ARG CUDA_PATCH=1
 ARG CUDA_VERSION=${CUDA_MAJOR}.${CUDA_MINOR}.${CUDA_PATCH}
 ARG CUDA_PACKAGES="nvcc_${CUDA_MAJOR}.${CUDA_MINOR} \
                    cudart_${CUDA_MAJOR}.${CUDA_MINOR} \
@@ -135,8 +135,8 @@ LABEL CUDA_VERSION="${CUDA_VERSION}"
 #
 # Installing Tensorrt
 #
-ARG TENSORRT_VERSION=8.5.3.1
-ARG TENSORRT_ZIP="TensorRT-${TENSORRT_VERSION}.Windows10.x86_64.cuda-11.8.zip"
+ARG TENSORRT_VERSION=8.6.1.6
+ARG TENSORRT_ZIP="TensorRT-${TENSORRT_VERSION}.Windows10.x86_64.cuda-12.0.zip"
 ARG TENSORRT_SOURCE=${TENSORRT_ZIP}
 # COPY ${TENSORRT_ZIP} /tmp/${TENSORRT_ZIP}
 ADD ${TENSORRT_SOURCE} /tmp/${TENSORRT_ZIP}
@@ -153,8 +153,8 @@ LABEL TENSORRT_VERSION="${TENSORRT_VERSION}"
 #
 # Installing CUDNN
 #
-ARG CUDNN_VERSION=8.8.1.3
-ARG CUDNN_ZIP=cudnn-windows-x86_64-${CUDNN_VERSION}_cuda11-archive.zip
+ARG CUDNN_VERSION=8.9.1.23
+ARG CUDNN_ZIP=cudnn-windows-x86_64-${CUDNN_VERSION}_cuda12-archive.zip
 ARG CUDNN_SOURCE=${CUDNN_ZIP}
 
 ADD ${CUDNN_SOURCE} /tmp/${CUDNN_ZIP}

diff --git a/README.md b/README.md
@@ -32,8 +32,8 @@
 
 **LATEST RELEASE: You are currently on the main branch which tracks
 under-development progress towards the next release. The current release is 
-version [2.33.0](https://github.com/triton-inference-server/server/tree/r23.04)
-and corresponds to the 23.04 container release on 
+version [2.34.0](https://github.com/triton-inference-server/server/tree/r23.05)
+and corresponds to the 23.05 container release on 
 [NVIDIA GPU Cloud (NGC)](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/tritonserver).**
 
 ----
@@ -88,16 +88,16 @@ Inference Server with the
 
 ```bash
 # Step 1: Create the example model repository 
-git clone -b r23.04 https://github.com/triton-inference-server/server.git
+git clone -b r23.05 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:23.04-py3 tritonserver --model-repository=/models
+docker run --gpus=1 --rm --net=host -v ${PWD}/model_repository:/models nvcr.io/nvidia/tritonserver:23.05-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:23.04-py3-sdk
+docker run -it --rm --net=host nvcr.io/nvidia/tritonserver:23.05-py3-sdk
 /workspace/install/bin/image_client -m densenet_onnx -c 3 -s INCEPTION /workspace/images/mug.jpg
 
 # Inference should return the following

diff --git a/build.py b/build.py
@@ -67,14 +67,15 @@
 # incorrectly load the other version of the openvino libraries.
 #
 TRITON_VERSION_MAP = {
+
     '2.35.0dev': (
         '23.06dev',  # triton container
-        '23.04',  # upstream container
-        '1.14.1',  # ORT
+        '23.05',  # upstream container
+        '1.15.0',  # ORT
         '2022.1.0',  # ORT OpenVINO
         '2022.1.0',  # Standalone OpenVINO
-        '2.2.9',  # DCGM version
-        'py38_4.12.0')  # Conda version.
+        '2.4.7',  # DCGM version
+        'py310_23.1.0-1')  # Conda version.
 }
 
 CORE_BACKENDS = ['ensemble']
@@ -830,7 +831,7 @@ def install_dcgm_libraries(dcgm_version, target_machine):
 ENV DCGM_VERSION {}
 # Install DCGM. Steps from https://developer.nvidia.com/dcgm#Downloads
 RUN curl -o /tmp/cuda-keyring.deb \
-    https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/sbsa/cuda-keyring_1.0-1_all.deb \
+    https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/sbsa/cuda-keyring_1.0-1_all.deb \
     && apt install /tmp/cuda-keyring.deb && rm /tmp/cuda-keyring.deb && \
     apt-get update && apt-get install -y datacenter-gpu-manager=1:{}
 '''.format(dcgm_version, dcgm_version)
@@ -839,7 +840,7 @@ def install_dcgm_libraries(dcgm_version, target_machine):
 ENV DCGM_VERSION {}
 # Install DCGM. Steps from https://developer.nvidia.com/dcgm#Downloads
 RUN curl -o /tmp/cuda-keyring.deb \
-    https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-keyring_1.0-1_all.deb \
+    https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.0-1_all.deb \
     && apt install /tmp/cuda-keyring.deb && rm /tmp/cuda-keyring.deb && \
     apt-get update && apt-get install -y datacenter-gpu-manager=1:{}
 '''.format(dcgm_version, dcgm_version)
@@ -857,9 +858,9 @@ def install_miniconda(conda_version, target_machine):
             .format(FLAGS.version))
     miniconda_url = f"https://repo.anaconda.com/miniconda/Miniconda3-{conda_version}-Linux-{target_machine}.sh"
     if target_machine == 'x86_64':
-        sha_sum = "3190da6626f86eee8abf1b2fd7a5af492994eb2667357ee4243975cdbb175d7a"
+        sha_sum = "32d73e1bc33fda089d7cd9ef4c1be542616bd8e437d1f77afeeaf7afdb019787"
     else:
-        sha_sum = "0c20f121dc4c8010032d64f8e9b27d79e52d28355eb8d7972eafc90652387777"
+        sha_sum = "80d6c306b015e1e3b01ea59dc66c676a81fa30279bc2da1f180a7ef7b2191d6e"
     return f'''
 RUN mkdir -p /opt/
 RUN wget "{miniconda_url}" -O miniconda.sh -q && \
@@ -945,13 +946,15 @@ def create_dockerfile_buildbase(ddir, dockerfile_name, argmap):
     mv /tmp/boost_1_80_0/boost /usr/include/boost
 
 # Server build requires recent version of CMake (FetchContent required)
-RUN wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc 2>/dev/null | \
-      gpg --dearmor - |  \
-      tee /etc/apt/trusted.gpg.d/kitware.gpg >/dev/null && \
-    apt-add-repository 'deb https://apt.kitware.com/ubuntu/ focal main' && \
+RUN apt update && 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 && \
-    apt-get install -y --no-install-recommends \
-      cmake-data=3.25.2-0kitware1ubuntu20.04.1 cmake=3.25.2-0kitware1ubuntu20.04.1
+    apt-get install -y --no-install-recommends cmake cmake-data 
 '''
 
         if FLAGS.enable_gpu:
@@ -1136,7 +1139,7 @@ def dockerfile_prepare_container_linux(argmap, backends, enable_gpu,
             software-properties-common \
             libb64-0d \
             libcurl4-openssl-dev \
-            libre2-5 \
+            libre2-9 \
             git \
             gperf \
             dirmngr \
@@ -1314,7 +1317,7 @@ def create_build_dockerfiles(container_build_dir, images, backends, repoagents,
         base_image = 'nvcr.io/nvidia/tritonserver:{}-py3-min'.format(
             FLAGS.upstream_container_version)
     else:
-        base_image = 'ubuntu:20.04'
+        base_image = 'ubuntu:22.04'
 
     dockerfileargmap = {
         'NVIDIA_BUILD_REF':

diff --git a/compose.py b/compose.py
@@ -434,7 +434,7 @@ def create_argmap(images, skip_pull):
                     "nvcr.io/nvidia/tritonserver:{}-cpu-only-py3".format(
                         FLAGS.container_version),
                 "min":
-                    "ubuntu:20.04"
+                    "ubuntu:22.04"
             }
     fail_if(
         len(images) < 2,

diff --git a/deploy/aws/values.yaml b/deploy/aws/values.yaml
@@ -27,7 +27,7 @@
 replicaCount: 1
 
 image:
-  imageName: nvcr.io/nvidia/tritonserver:23.04-py3
+  imageName: nvcr.io/nvidia/tritonserver:23.05-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
@@ -26,7 +26,7 @@
 
 apiVersion: v1
 # appVersion is the Triton version; update when changing release
-appVersion: "2.33.0"
+appVersion: "2.34.0"
 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
@@ -27,7 +27,7 @@
 replicaCount: 1
 
 image:
-  imageName: nvcr.io/nvidia/tritonserver:23.04-py3
+  imageName: nvcr.io/nvidia/tritonserver:23.05-py3
   pullPolicy: IfNotPresent
   numGpus: 1
   serverCommand: tritonserver
@@ -46,13 +46,13 @@ image:
     # Model Control Mode (Optional, default: none)
     #
     # To set model control mode, uncomment and configure below
-    # See https://github.com/triton-inference-server/server/blob/r23.04/docs/model_management.md
+    # See https://github.com/triton-inference-server/server/blob/r23.05/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/r23.04/README.md
+    # see https://github.com/triton-inference-server/server/blob/r23.05/README.md
     #  for more details
 
 service:

diff --git a/deploy/gcp/values.yaml b/deploy/gcp/values.yaml
@@ -27,7 +27,7 @@
 replicaCount: 1
 
 image:
-  imageName: nvcr.io/nvidia/tritonserver:23.04-py3
+  imageName: nvcr.io/nvidia/tritonserver:23.05-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
@@ -33,7 +33,7 @@ metadata:
   namespace: default
 spec:
   containers:
-  - image: nvcr.io/nvidia/tritonserver:23.04-py3-sdk
+  - image: nvcr.io/nvidia/tritonserver:23.05-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
@@ -27,8 +27,8 @@
 export REGISTRY=gcr.io/$(gcloud config get-value project | tr ':' '/')
 export APP_NAME=tritonserver
 export MAJOR_VERSION=2.33
-export MINOR_VERSION=2.33.0
-export NGC_VERSION=23.04-py3
+export MINOR_VERSION=2.34.0
+export NGC_VERSION=23.05-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
@@ -28,4 +28,4 @@ apiVersion: v1
 appVersion: "2.33"
 description: Triton Inference Server
 name: triton-inference-server
-version: 2.33.0
+version: 2.34.0
diff --git a/deploy/gke-marketplace-app/server-deployer/chart/triton/values.yaml b/deploy/gke-marketplace-app/server-deployer/chart/triton/values.yaml
@@ -32,13 +32,13 @@ tritonProtocol: HTTP
 # HPA GPU utilization autoscaling target
 HPATargetAverageValue: 85
 modelRepositoryPath: gs://triton_sample_models/23_04
-publishedVersion: '2.33.0'
+publishedVersion: '2.34.0'
 gcpMarketplace: true
 
 image:
   registry: gcr.io
   repository: nvidia-ngc-public/tritonserver
-  tag: 23.04-py3
+  tag: 23.05-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
@@ -27,7 +27,7 @@
 x-google-marketplace:
   schemaVersion: v2
   applicationApiVersion: v1beta1
-  publishedVersion: '2.33.0'
+  publishedVersion: '2.34.0'
   publishedVersionMetadata:
     releaseNote: >-
       Initial release.