From 67a7e9994b4ad3187fba66c93a1074ec90b83554 Mon Sep 17 00:00:00 2001 From: fpetrini15 Date: Mon, 8 Jul 2024 09:17:21 -0700 Subject: [PATCH 1/4] Remove "LATEST RELEASE..." --- README.md | 5 ----- 1 file changed, 5 deletions(-) diff --git a/README.md b/README.md index 38b4759c48..f5f037f523 100644 --- a/README.md +++ b/README.md @@ -30,11 +30,6 @@ [![License](https://img.shields.io/badge/License-BSD3-lightgrey.svg)](https://opensource.org/licenses/BSD-3-Clause) -> [!WARNING] -> ##### LATEST RELEASE -> You are currently on the `main` branch which tracks under-development progress towards the next release. -> The current release is version [2.47.0](https://github.com/triton-inference-server/server/releases/latest) and corresponds to the 24.06 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 multiple deep learning and machine learning frameworks, including TensorRT, From 0f687d2cf792553dcd5d13c06ef86e66ef15e22d Mon Sep 17 00:00:00 2001 From: fpetrini15 Date: Mon, 8 Jul 2024 13:10:23 -0700 Subject: [PATCH 2/4] Update README and versions for 2.48.0 / 24.07 --- Dockerfile.sdk | 2 +- Dockerfile.win10.min | 20 +- README.md | 232 +----------------- TRITON_VERSION | 2 +- build.py | 8 +- deploy/aws/values.yaml | 4 +- deploy/fleetcommand/Chart.yaml | 4 +- deploy/fleetcommand/values.yaml | 8 +- deploy/gcp/values.yaml | 4 +- .../perf-analyzer-script/triton_client.yaml | 4 +- .../server-deployer/build_and_push.sh | 8 +- .../server-deployer/chart/triton/Chart.yaml | 6 +- .../server-deployer/chart/triton/values.yaml | 8 +- .../server-deployer/data-test/schema.yaml | 4 +- .../server-deployer/schema.yaml | 6 +- .../gke-marketplace-app/trt-engine/README.md | 8 +- deploy/k8s-onprem/values.yaml | 4 +- deploy/oci/values.yaml | 4 +- docs/customization_guide/build.md | 8 +- docs/customization_guide/compose.md | 20 +- docs/customization_guide/test.md | 4 +- docs/generate_docs.py | 4 +- docs/user_guide/custom_operations.md | 8 +- docs/user_guide/performance_tuning.md | 6 +- qa/common/gen_jetson_trt_models | 4 +- qa/common/gen_qa_custom_ops | 4 +- qa/common/gen_qa_model_repository | 2 +- 27 files changed, 86 insertions(+), 310 deletions(-) diff --git a/Dockerfile.sdk b/Dockerfile.sdk index 9e83ecca47..e92b4bcb89 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:24.06-py3-min +ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.07-py3-min ARG TRITON_CLIENT_REPO_SUBDIR=clientrepo ARG TRITON_COMMON_REPO_TAG=main diff --git a/Dockerfile.win10.min b/Dockerfile.win10.min index 7d954d62de..fb2a543238 100644 --- a/Dockerfile.win10.min +++ b/Dockerfile.win10.min @@ -1,4 +1,4 @@ -# Copyright 2021-2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. +# Copyright 2021-2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved. # # Redistribution and use in source and binary forms, with or without # modification, are permitted provided that the following conditions @@ -37,9 +37,9 @@ RUN choco install unzip -y # # Installing TensorRT # -ARG TENSORRT_VERSION=10.0.1.6 -ARG TENSORRT_ZIP="TensorRT-${TENSORRT_VERSION}.Windows10.x86_64.cuda-12.4.zip" -ARG TENSORRT_SOURCE=https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/10.0.1/zip/TensorRT-10.0.1.6.Windows10.win10.cuda-12.4.zip +ARG TENSORRT_VERSION=10.2.0.19 +ARG TENSORRT_ZIP="TensorRT-${TENSORRT_VERSION}.Windows10.x86_64.cuda-12.5.zip" +ARG TENSORRT_SOURCE=https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/10.2.0/zip/TensorRT-10.2.0.19.Windows10.x86_64.cuda-12.5.zip # COPY ${TENSORRT_ZIP} /tmp/${TENSORRT_ZIP} ADD ${TENSORRT_SOURCE} /tmp/${TENSORRT_ZIP} RUN unzip /tmp/%TENSORRT_ZIP% @@ -51,9 +51,9 @@ LABEL TENSORRT_VERSION="${TENSORRT_VERSION}" # # Installing cuDNN # -ARG CUDNN_VERSION=9.1.0.70 +ARG CUDNN_VERSION=9.2.1.18 ARG CUDNN_ZIP=cudnn-windows-x86_64-${CUDNN_VERSION}_cuda12-archive.zip -ARG CUDNN_SOURCE=https://developer.download.nvidia.com/compute/cudnn/redist/cudnn/windows-x86_64/cudnn-windows-x86_64-9.1.0.70_cuda12-archive.zip +ARG CUDNN_SOURCE=https://developer.download.nvidia.com/compute/cudnn/redist/cudnn/windows-x86_64/cudnn-windows-x86_64-9.2.1.18_cuda12-archive.zip ADD ${CUDNN_SOURCE} /tmp/${CUDNN_ZIP} RUN unzip /tmp/%CUDNN_ZIP% RUN move cudnn-* cudnn @@ -125,7 +125,7 @@ WORKDIR / # # Installing Vcpkg # -ARG VCPGK_VERSION=2024.03.19 +ARG VCPGK_VERSION=2024.06.15 RUN git clone --single-branch --depth=1 -b %VCPGK_VERSION% https://github.com/microsoft/vcpkg.git WORKDIR /vcpkg RUN bootstrap-vcpkg.bat @@ -150,7 +150,7 @@ WORKDIR / # ARG CUDA_MAJOR=12 ARG CUDA_MINOR=5 -ARG CUDA_PATCH=0 +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} \ @@ -175,7 +175,7 @@ RUN copy "%CUDA_INSTALL_ROOT_WP%\extras\visual_studio_integration\MSBuildExtensi RUN setx PATH "%CUDA_INSTALL_ROOT_WP%\bin;%PATH%" -ARG CUDNN_VERSION=9.1.0.70 +ARG CUDNN_VERSION=9.2.1.18 ENV CUDNN_VERSION ${CUDNN_VERSION} COPY --from=dependency_base /cudnn /cudnn RUN copy cudnn\bin\cudnn*.dll "%CUDA_INSTALL_ROOT_WP%\bin\." @@ -183,7 +183,7 @@ RUN copy cudnn\lib\x64\cudnn*.lib "%CUDA_INSTALL_ROOT_WP%\lib\x64\." RUN copy cudnn\include\cudnn*.h "%CUDA_INSTALL_ROOT_WP%\include\." LABEL CUDNN_VERSION="${CUDNN_VERSION}" -ARG TENSORRT_VERSION=10.0.1.6 +ARG TENSORRT_VERSION=10.2.0.19 ENV TRT_VERSION ${TENSORRT_VERSION} COPY --from=dependency_base /TensorRT /TensorRT RUN setx PATH "c:\TensorRT\lib;%PATH%" diff --git a/README.md b/README.md index f5f037f523..3f812793b6 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,5 @@