diff --git a/Dockerfile.sdk b/Dockerfile.sdk index a1e75e96d2..59bdaea509 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:25.11-py3-min +ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:25.12-py3-min ARG TRITON_CLIENT_REPO_SUBDIR=clientrepo ARG TRITON_REPO_ORGANIZATION=http://github.com/triton-inference-server @@ -41,7 +41,7 @@ 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=4.4.0-1 +ARG DCGM_VERSION=4.4.2-1 ARG NVIDIA_TRITON_SERVER_SDK_VERSION=unknown ARG NVIDIA_BUILD_ID=unknown diff --git a/README.md b/README.md index 9035fa2bc4..8414dfa7e9 100644 --- a/README.md +++ b/README.md @@ -27,11 +27,6 @@ --> [![License](https://img.shields.io/badge/License-BSD3-lightgrey.svg)](https://opensource.org/licenses/BSD-3-Clause) ->[!WARNING] ->You are currently on the `main` branch which tracks under-development progress ->towards the next release. The current release is version [2.63.0](https://github.com/triton-inference-server/server/releases/latest) ->and corresponds to the 25.11 container release on NVIDIA GPU Cloud (NGC). - # Triton Inference Server Triton Inference Server is an open source inference serving software that @@ -61,7 +56,7 @@ Major features include: - Provides [Backend API](https://github.com/triton-inference-server/backend) that allows adding custom backends and pre/post processing operations - Supports writing custom backends in python, a.k.a. - [Python-based backends.](https://github.com/triton-inference-server/backend/blob/main/docs/python_based_backends.md#python-based-backends) + [Python-based backends.](https://github.com/triton-inference-server/backend/blob/r25.12/docs/python_based_backends.md#python-based-backends) - Model pipelines using [Ensembling](docs/user_guide/architecture.md#ensemble-models) or [Business Logic Scripting @@ -90,16 +85,16 @@ Inference Server with the ```bash # Step 1: Create the example model repository -git clone -b r25.11 https://github.com/triton-inference-server/server.git +git clone -b r25.12 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:25.11-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:25.12-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:25.11-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:25.12-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': @@ -172,10 +167,10 @@ configuration](docs/user_guide/model_configuration.md) for the model. [Python](https://github.com/triton-inference-server/python_backend), and more - Not all the above backends are supported on every platform supported by Triton. Look at the - [Backend-Platform Support Matrix](https://github.com/triton-inference-server/backend/blob/main/docs/backend_platform_support_matrix.md) + [Backend-Platform Support Matrix](https://github.com/triton-inference-server/backend/blob/r25.12/docs/backend_platform_support_matrix.md) to learn which backends are supported on your target platform. - Learn how to [optimize performance](docs/user_guide/optimization.md) using the - [Performance Analyzer](https://github.com/triton-inference-server/perf_analyzer/blob/main/README.md) + [Performance Analyzer](https://github.com/triton-inference-server/perf_analyzer/blob/r25.12/README.md) and [Model Analyzer](https://github.com/triton-inference-server/model_analyzer) - Learn how to [manage loading and unloading models](docs/user_guide/model_management.md) in @@ -189,14 +184,14 @@ A Triton *client* application sends inference and other requests to Triton. The [Python and C++ client libraries](https://github.com/triton-inference-server/client) provide APIs to simplify this communication. -- Review client examples for [C++](https://github.com/triton-inference-server/client/blob/main/src/c%2B%2B/examples), - [Python](https://github.com/triton-inference-server/client/blob/main/src/python/examples), - and [Java](https://github.com/triton-inference-server/client/blob/main/src/java/src/main/java/triton/client/examples) +- Review client examples for [C++](https://github.com/triton-inference-server/client/blob/r25.12/src/c%2B%2B/examples), + [Python](https://github.com/triton-inference-server/client/blob/r25.12/src/python/examples), + and [Java](https://github.com/triton-inference-server/client/blob/r25.12/src/java/src/main/java/triton/client/examples) - Configure [HTTP](https://github.com/triton-inference-server/client#http-options) and [gRPC](https://github.com/triton-inference-server/client#grpc-options) client options - Send input data (e.g. a jpeg image) directly to Triton in the [body of an HTTP - request without any additional metadata](https://github.com/triton-inference-server/server/blob/main/docs/protocol/extension_binary_data.md#raw-binary-request) + request without any additional metadata](https://github.com/triton-inference-server/server/blob/r25.12/docs/protocol/extension_binary_data.md#raw-binary-request) ### Extend Triton @@ -205,7 +200,7 @@ designed for modularity and flexibility - [Customize Triton Inference Server container](docs/customization_guide/compose.md) for your use case - [Create custom backends](https://github.com/triton-inference-server/backend) - in either [C/C++](https://github.com/triton-inference-server/backend/blob/main/README.md#triton-backend-api) + in either [C/C++](https://github.com/triton-inference-server/backend/blob/r25.12/README.md#triton-backend-api) or [Python](https://github.com/triton-inference-server/python_backend) - Create [decoupled backends and models](docs/user_guide/decoupled_models.md) that can send multiple responses for a request or not send any responses for a request diff --git a/TRITON_VERSION b/TRITON_VERSION index 952e951595..d1524d4046 100644 --- a/TRITON_VERSION +++ b/TRITON_VERSION @@ -1 +1 @@ -2.64.0dev +2.64.0 diff --git a/build.py b/build.py index bd2bb8a7ed..f75e49b31e 100755 --- a/build.py +++ b/build.py @@ -71,14 +71,14 @@ # DEFAULT_TRITON_VERSION_MAP = { - "release_version": "2.64.0dev", - "triton_container_version": "25.11dev", - "upstream_container_version": "25.11", + "release_version": "2.64.0", + "triton_container_version": "25.12", + "upstream_container_version": "25.12", "ort_version": "1.23.2", "ort_openvino_version": "2025.4.0", "standalone_openvino_version": "2025.4.0", "dcgm_version": "4.4.2-1", - "vllm_version": "0.11.0", + "vllm_version": "0.11.1", "rhel_py_version": "3.12.3", } diff --git a/deploy/aws/values.yaml b/deploy/aws/values.yaml index cc8748f0d1..6ccd3f5612 100644 --- a/deploy/aws/values.yaml +++ b/deploy/aws/values.yaml @@ -27,7 +27,7 @@ replicaCount: 1 image: - imageName: nvcr.io/nvidia/tritonserver:25.11-py3 + imageName: nvcr.io/nvidia/tritonserver:25.12-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 b0e42586ca..b923491e4d 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: 2.63.0" +appVersion: 2.64.0 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 d36b0f5d13..6cbbb50553 100644 --- a/deploy/fleetcommand/values.yaml +++ b/deploy/fleetcommand/values.yaml @@ -27,7 +27,7 @@ replicaCount: 1 image: - imageName: nvcr.io/nvidia/tritonserver:25.11-py3 + imageName: nvcr.io/nvidia/tritonserver:25.12-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/r25.11/docs/user_guide/model_management.md + # See https://github.com/triton-inference-server/server/blob/r25.12/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/r25.11/README.md + # see https://github.com/triton-inference-server/server/blob/r25.12/README.md # for more details service: diff --git a/deploy/gcp/values.yaml b/deploy/gcp/values.yaml index 53d960feb8..97ceba2606 100644 --- a/deploy/gcp/values.yaml +++ b/deploy/gcp/values.yaml @@ -27,7 +27,7 @@ replicaCount: 1 image: - imageName: nvcr.io/nvidia/tritonserver:25.11-py3 + imageName: nvcr.io/nvidia/tritonserver:25.12-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 47fe79cec1..181005d382 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:25.11-py3-sdk + - image: nvcr.io/nvidia/tritonserver:25.12-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 79e72774f4..22c57b09db 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=2.63 -export MINOR_VERSION=2.63.0 -export NGC_VERSION=25.11-py3 +export MAJOR_VERSION=2.64 +export MINOR_VERSION=2.64.0 +export NGC_VERSION=25.12-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 3063bd0270..0bec3222a7 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: "2.63" +appVersion: "2.64" description: Triton Inference Server name: triton-inference-server -version: 2.63.0 +version: 2.64.0 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 2aa7fc63d1..d0d0b87493 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/25.11 -publishedVersion: '2.63.0' +modelRepositoryPath: gs://triton_sample_models/25.12 +publishedVersion: '2.64.0' gcpMarketplace: true image: registry: gcr.io repository: nvidia-ngc-public/tritonserver - tag: 25.11-py3 + tag: 25.12-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 1f19f2e3b0..add506981a 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: '2.63.0' + publishedVersion: '2.64.0' 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 18bfeb9005..dc1f75ae7c 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: '2.63.0' + publishedVersion: '2.64.0' 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/25.11 + default: gs://triton_sample_models/25.12 image.ldPreloadPath: type: string title: Leave this empty by default. Triton allows users to create custom layers for backend such as TensorRT plugin, 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 e7a3af632b..20cdb977d9 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:25.11-py3 + -v ~:/scripts nvcr.io/nvidia/tensorrt:25.12-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/25.11/bert/1/model.plan +gsutil cp bert_large_int8_bs1_s128.engine gs://triton_sample_models/25.12/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/25.11/` 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/25.12/` should be updated accordingly with the correct version. diff --git a/deploy/k8s-onprem/values.yaml b/deploy/k8s-onprem/values.yaml index 96073f0014..e7f6fd14d5 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:25.11-py3 + imageName: nvcr.io/nvidia/tritonserver:25.12-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 a0910fc1e2..971ae37787 100644 --- a/deploy/oci/values.yaml +++ b/deploy/oci/values.yaml @@ -27,7 +27,7 @@ replicaCount: 1 image: - imageName: nvcr.io/nvidia/tritonserver:25.11-py3 + imageName: nvcr.io/nvidia/tritonserver:25.12-py3 pullPolicy: IfNotPresent modelRepositoryPath: s3://https://.compat.objectstorage..oraclecloud.com:443/triton-inference-server-repository numGpus: 1 diff --git a/docs/introduction/compatibility.md b/docs/introduction/compatibility.md index f4d254058c..6e5f56534e 100644 --- a/docs/introduction/compatibility.md +++ b/docs/introduction/compatibility.md @@ -38,6 +38,7 @@ | Triton release version | NGC Tag | Python version | Torch version | TensorRT version | TensorRT-LLM version | CUDA version | CUDA Driver version | Size | | --- | --- | --- | --- | --- | --- | --- | --- | --- | +| 25.12 | nvcr.io/nvidia/tritonserver:25.12-trtllm-python-py3 | Python 3.12.3 | 2.9.0a0+145a3a7bda.nv25.10 | 10.13.3.9 | 1.0.3.2510 | 13.0.2.006 | 580.95.05 | 16.04 GB | | 25.11 | nvcr.io/nvidia/tritonserver:25.11-trtllm-python-py3 | Python 3.12.3 | 2.9.0a0+145a3a7bda.nv25.10 | 10.13.3.9 | 1.0.3.2510 | 13.0.2.006 | 580.95.05 | 12.25 GB | | 25.10 | nvcr.io/nvidia/tritonserver:25.10-trtllm-python-py3 | Python 3.12.3 | 2.8.0a0+5228986c39.nv25.6 | 10.11.0.33 | 1.0.0 | 12.9.1.010 | 575.57.08 | 16.21 GB | | 25.09 | nvcr.io/nvidia/tritonserver:25.09-trtllm-python-py3 | Python 3.12.3 | 2.8.0a0+5228986c39.nv25.6 | 10.11.0.33 | 1.0.0 | 12.9.1.010 | 575.57.08 | 16.25 GB | @@ -63,6 +64,7 @@ | Triton release version | NGC Tag | Python version | vLLM version | CUDA version | CUDA Driver version | Size | | --- | --- | --- | --- | --- | --- | --- | +| 25.12 | nvcr.io/nvidia/tritonserver:25.12-vllm-python-py3 | Python 3.12.3 | 0.11.1+9114fd76.nv25.12.cu131 | 13.1.0.036 | 590.44.01 | 8.54G | | 25.11 | nvcr.io/nvidia/tritonserver:25.11-vllm-python-py3 | Python 3.12.3 | 0.11.0+582e4e37.nv25.11.cu130 | 13.0.2.006 | 580.95.05 | 8.72G | | 25.10 | nvcr.io/nvidia/tritonserver:25.10-vllm-python-py3 | Python 3.12.3 | 0.10.2+9dd9ca32.nv25.10.cu130 | 13.0.2.006 | 580.95.05 | 8.34G | | 25.09 | nvcr.io/nvidia/tritonserver:25.09-vllm-python-py3 | Python 3.12.3 | 0.10.1.1+381074ae.nv25.9.cu130 | 13.0.1.012 | 580.82.07 | 7.78G | @@ -88,6 +90,7 @@ | Triton release version | ONNX Runtime | | --- | --- | +| 25.12 | 1.23.2 | | 25.11 | 1.23.2 | | 25.10 | 1.23.1 | | 25.09 | 1.23.0 | diff --git a/docs/introduction/release_notes.md b/docs/introduction/release_notes.md index d73bfd9df0..6c21f2942f 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 25.11](https://docs.nvidia.com/deeplearning/triton-inference-server/release-notes/rel-25-10.html#rel-25-10) +# [Triton Inference Server Release 25.12](https://docs.nvidia.com/deeplearning/triton-inference-server/release-notes/rel-25-12.html#rel-25-12) -The Triton Inference Server container image, release 25.11, is available +The Triton Inference Server container image, release 25.12, 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 8c4906faf0..6d66696d7e 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:25.11-vllm-python-py3 + nvcr.io/nvidia/tritonserver:25.12-vllm-python-py3 ``` 2. Launch the OpenAI-compatible Triton Inference Server: @@ -360,7 +360,7 @@ Currently, OpenAI-Compatible Frontend supports loading embedding models and embe docker run -it --net=host --gpus all --rm \ -v ${HOME}/.cache/huggingface:/root/.cache/huggingface \ -e HF_TOKEN \ - nvcr.io/nvidia/tritonserver:25.11-vllm-python-py3 + nvcr.io/nvidia/tritonserver:25.12-vllm-python-py3 ``` 2. Launch the OpenAI-compatible Triton Inference Server: @@ -456,7 +456,7 @@ docker run -it --net=host --gpus all --rm \ -v ${HOME}/.cache/huggingface:/root/.cache/huggingface \ -e HF_TOKEN \ -e TRTLLM_ORCHESTRATOR=1 \ - nvcr.io/nvidia/tritonserver:24.11-trtllm-python-py3 + nvcr.io/nvidia/tritonserver:25.12-trtllm-python-py3 ``` 2. Install dependencies inside the container: diff --git a/qa/common/gen_jetson_trt_models b/qa/common/gen_jetson_trt_models index b763d2c490..edcb3748cf 100755 --- a/qa/common/gen_jetson_trt_models +++ b/qa/common/gen_jetson_trt_models @@ -34,7 +34,7 @@ # Make all generated files accessible outside of container umask 0000 # Set the version of the models -TRITON_VERSION=${TRITON_VERSION:=25.11} +TRITON_VERSION=${TRITON_VERSION:=25.12} # Set the CUDA device to use CUDA_DEVICE=${RUNNER_ID:=0} # Set TensorRT image diff --git a/qa/common/gen_qa_model_repository b/qa/common/gen_qa_model_repository index 1c0458ba58..501fc2508a 100755 --- a/qa/common/gen_qa_model_repository +++ b/qa/common/gen_qa_model_repository @@ -60,7 +60,7 @@ log_message.status "Changing working directory to the script directory to: " "${ cd ${TRITON_MDLS_BASE_SCRIPT_DIR} log_message.status "define: default values" -TRITON_VERSION=${TRITON_VERSION:=25.11} +TRITON_VERSION=${TRITON_VERSION:=25.12} ONNX_VERSION=1.16.1 ONNX_OPSET=0 OPENVINO_VERSION=2024.5.0