Merge branch 'main' into mwittwer/fix_python_runtime_autofill

Author: mattwittwer

Dockerfile.QA

@@ -147,7 +147,8 @@ RUN mkdir -p qa/common && \
     cp bin/logging_test qa/L0_logging/. && \
     cp bin/backend_output_detail_test qa/L0_backend_output_detail/. && \
     cp -r deploy/mlflow-triton-plugin qa/L0_mlflow/. && \
-    cp bin/input_byte_size_test qa/L0_input_validation/.
+    cp bin/input_byte_size_test qa/L0_input_validation/. && \
+    cp bin/instance_queue_test qa/L0_batcher/.
 
 RUN mkdir -p qa/pkgs && \
     cp python/triton*.whl qa/pkgs/. && \

Dockerfile.sdk

@@ -29,7 +29,7 @@
 #
 
 # Base image on the minimum Triton container
-ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:26.06-py3-min
+ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:26.07-py3-min
 
 ARG TRITON_CLIENT_REPO_SUBDIR=clientrepo
 ARG TRITON_REPO_ORGANIZATION=http://github.com/triton-inference-server

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 [2.70.0](https://github.com/triton-inference-server/server/releases/latest)
->and corresponds to the 26.06 container release on NVIDIA GPU Cloud (NGC).
+>towards the next release. The current release is version [2.71.0](https://github.com/triton-inference-server/server/releases/latest)
+>and corresponds to the 26.07 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 r26.06 https://github.com/triton-inference-server/server.git
+git clone -b r26.07 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:26.06-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:26.07-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:26.06-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:26.07-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

@@ -74,7 +74,7 @@
 DEFAULT_TRITON_VERSION_MAP = {
     "release_version": "2.72.0dev",
     "triton_container_version": "26.08dev",
-    "upstream_container_version": "26.06",
+    "upstream_container_version": "26.07",
     "ort_version": "1.27.0",
     "ort_openvino_version": "2026.2.0",
     "standalone_openvino_version": "2026.2.0",

deploy/aws/values.yaml

@@ -27,7 +27,7 @@
 replicaCount: 1
 
 image:
-  imageName: nvcr.io/nvidia/tritonserver:26.06-py3
+  imageName: nvcr.io/nvidia/tritonserver:26.07-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: 2.70.0
+appVersion: 2.71.0
 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:26.06-py3
+  imageName: nvcr.io/nvidia/tritonserver:26.07-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/r26.06/docs/user_guide/model_management.md
+    # See https://github.com/triton-inference-server/server/blob/r26.07/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/r26.06/README.md
+    # see https://github.com/triton-inference-server/server/blob/r26.07/README.md
     #  for more details
 
 service:

deploy/gcp/values.yaml

@@ -27,7 +27,7 @@
 replicaCount: 1
 
 image:
-  imageName: nvcr.io/nvidia/tritonserver:26.06-py3
+  imageName: nvcr.io/nvidia/tritonserver:26.07-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:26.06-py3-sdk
+  - image: nvcr.io/nvidia/tritonserver:26.07-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=2.67
-export MINOR_VERSION=2.70.0
-export NGC_VERSION=26.06-py3
+export MINOR_VERSION=2.71.0
+export NGC_VERSION=26.07-py3
 
 docker pull nvcr.io/nvidia/$APP_NAME:$NGC_VERSION