chore: Upgrade to CUDA 12.1 and CuDNN 8.9

- Upgrade CUDA version across CI, dependencies, and build systems - Upgrade versions for Torch, CuDNN, TensorRT, and other dependencies in accordance with new CUDA version 12.1 - Upgrade Torch nightly date to latest available
pytorch · Jun 14, 2023 · 7338f9e · 7338f9e
1 parent 1735088
commit 7338f9e
Show file tree

Hide file tree

Showing 13 changed files with 74 additions and 85 deletions.
diff --git a/.circleci/config.yml b/.circleci/config.yml
@@ -92,17 +92,9 @@ commands:
                     key: cmake-<< parameters.cache-key >>-<< parameters.version >>
                     paths:
                         - << parameters.install-dir >>
-  uninstall-cuda:
-    description: "Uninstall CUDA-11.4"
-    steps:
-      - run:
-          name: "Uninstall CUDA-11.4"
-          command: |
-            sudo apt-get --purge remove "cuda*" "nsight*"
-            sudo apt-get --purge remove "*nvidia*"
 
   install-cudnn:
-    description: "Install CUDNN 8.8.0"
+    description: "Install CUDNN 8.9.1"
     parameters:
       os:
         type: string
@@ -112,10 +104,10 @@ commands:
         default: "x86_64"
       cudnn-version:
         type: string
-        default: "8.8.0.121"
+        default: "8.9.1.23"
       cuda-version:
         type: string
-        default: "cuda11.8"
+        default: "cuda12.1"
     steps:
       - run:
           name: Install CUDNN
@@ -149,13 +141,13 @@ commands:
         default: "amd64"
       cuda-pkg-name:
         type: string
-        default: "cuda-toolkit-11-8"
+        default: "cuda-toolkit-12-1"
       cuda-pkg-version:
         type: string
-        default: "11-8"
+        default: "12-1"
       cuda-version:
         type: string
-        default: "11.8.0"
+        default: "12.1.1"
     steps:
       - run:
           name: Install CUDA
@@ -188,19 +180,16 @@ commands:
         default: "amd64"
       cuda-pkg-name:
         type: string
-        default: "cuda-toolkit-11-8"
+        default: "cuda-toolkit-12-1"
       cuda-pkg-version:
         type: string
-        default: "11-8"
-      cuda-version:
-        type: string
-        default: "11.8.0"
+        default: "12-0"
       cuda-string-version:
         type: string
-        default: "cuda11.8"
+        default: "cuda12.1"
       cudnn-version:
         type: string
-        default: "8.8.0.121"
+        default: "8.9.1.23"
       trt-version-short:
         type: string
         default: "8.6.1"
@@ -252,7 +241,7 @@ commands:
           default: "8.6.1"
         cudnn-version-long:
           type: string
-          default: "8.8.0.121"
+          default: "8.9.1.23"
       steps:
         - run:
             name: Set up python environment
@@ -261,21 +250,21 @@ commands:
               pip3 install wheel setuptools
               pip3 install nvidia-pyindex
               pip3 install tabulate
-              pip3 install tensorrt==<< parameters.trt-version-long >> nvidia-cudnn-cu11==<< parameters.cudnn-version-long >>
+              pip3 install tensorrt==<< parameters.trt-version-long >> nvidia-cudnn-cu12==<< parameters.cudnn-version-long >>
               pip3 install pytest parameterized expecttest nox
 
   install-torch-from-index:
     description: "Install Pytorch"
     parameters:
       torch-build:
         type: string
-        default: "2.1.0.dev20230605+cu118"
+        default: "2.1.0.dev20230613+cu121"
       torchvision-build:
         type: string
-        default: "0.16.0.dev20230605+cu118"
+        default: "0.16.0.dev20230613+cu121"
       torch-build-index:
         type: string
-        default: "https://download.pytorch.org/whl/nightly/cu118"
+        default: "https://download.pytorch.org/whl/nightly/cu121"
     steps:
       - run:
           name: Install Torch
@@ -293,7 +282,7 @@ commands:
       - run:
           name: Build torch-tensorrt python release (pre-cxx11-abi)
           command: |
-            export CUDA_HOME=/usr/local/cuda-11.8/
+            export CUDA_HOME=/usr/local/cuda-12.1/
             mv toolchains/ci_workspaces/WORKSPACE.<< parameters.platform >> WORKSPACE
             cd py
             python3 -m pip install wheel setuptools
@@ -313,7 +302,7 @@ commands:
       - run:
           name: Build torch-tensorrt python legacy release (pre-cxx11-abi)
           command: |
-            export CUDA_HOME=/usr/local/cuda-11.8/
+            export CUDA_HOME=/usr/local/cuda-12.1/
             mv toolchains/ci_workspaces/WORKSPACE.<< parameters.platform >> WORKSPACE
             cd py
             python3 -m pip install wheel setuptools
@@ -345,7 +334,7 @@ commands:
             - run:
                 name: Build torch-tensorrt python release package
                 command: |
-                  export CUDA_HOME=/usr/local/cuda-11.8/
+                  export CUDA_HOME=/usr/local/cuda-12.1/
                   cd ~/project/py
                   python3 setup.py bdist_wheel --use-cxx11-abi --release
                   python3 setup.py install --use-cxx11-abi --release
@@ -357,7 +346,7 @@ commands:
             - run:
                 name: Build torch-tensorrt python package
                 command: |
-                  export CUDA_HOME=/usr/local/cuda-11.8/
+                  export CUDA_HOME=/usr/local/cuda-12.1/
                   cd ~/project/py
                   python3 setup.py bdist_wheel --use-cxx11-abi
                   python3 setup.py install --use-cxx11-abi
@@ -375,7 +364,7 @@ commands:
       - run:
           name: Build torch-tensorrt python release with only the fx backend
           command: |
-            export CUDA_HOME=/usr/local/cuda-11.8/
+            export CUDA_HOME=/usr/local/cuda-12.1/
             mv toolchains/ci_workspaces/WORKSPACE.<< parameters.platform >> WORKSPACE
             cd py
             python3 -m pip install wheel setuptools
@@ -447,7 +436,7 @@ commands:
           name: Build torch-tensorrt library with CMake
           command: |
             mkdir build
-            export PATH=$PATH:/usr/local/cuda-11.8/bin
+            export PATH=$PATH:/usr/local/cuda-12.1/bin
             ~/cmake/bin/cmake -S. -Bbuild \
               -DCMAKE_MODULE_PATH=cmake/Module \
               -DTorch_DIR=/opt/circleci/.pyenv/versions/3.9.4/lib/python3.9/site-packages/torch/share/cmake/Torch \
@@ -499,7 +488,7 @@ commands:
           name: Run core / C++ tests
           no_output_timeout: 15m
           environment:
-            LD_LIBRARY_PATH: "/opt/circleci/.pyenv/versions/3.9.4/lib/python3.9/site-packages/torch_tensorrt.libs:/home/circleci/project/bazel-project/external/libtorch_pre_cxx11_abi/lib/:/home/circleci/project/bazel-project/external/tensorrt/lib/:/usr/local/cuda-11.8/lib64/:$LD_LIBRARY_PATH"
+            LD_LIBRARY_PATH: "/opt/circleci/.pyenv/versions/3.9.4/lib/python3.9/site-packages/torch_tensorrt.libs:/home/circleci/project/bazel-project/external/libtorch_pre_cxx11_abi/lib/:/home/circleci/project/bazel-project/external/tensorrt/lib/:/usr/local/cuda-12.1/lib64/:$LD_LIBRARY_PATH"
           command: |
             set -e
             mv toolchains/ci_workspaces/WORKSPACE.<< parameters.platform >> WORKSPACE
@@ -529,7 +518,7 @@ commands:
           environment:
             USE_HOST_DEPS: "1"
             PYT_PATH: "/opt/circleci/.pyenv/versions/3.9.4/lib/python3.9/site-packages/"
-            LD_LIBRARY_PATH: "/usr/lib/x86_64-linux-gnu/:/usr/local/cuda-11.8/lib64/:$LD_LIBRARY_PATH"
+            LD_LIBRARY_PATH: "/usr/lib/x86_64-linux-gnu/:/usr/local/cuda-12.1/lib64/:$LD_LIBRARY_PATH"
           command: |
             set -e
             mkdir -p /tmp/artifacts/test_results
@@ -819,7 +808,7 @@ jobs:
         type: boolean
         default: false
     machine:
-      image: linux-cuda-11:2023.02.1
+      image: linux-cuda-12:2023.05.1
     resource_class: gpu.nvidia.small
     steps:
       - checkout
@@ -881,7 +870,7 @@ jobs:
       cudnn-version:
         type: string
     machine:
-      image: linux-cuda-11:2023.02.1
+      image: linux-cuda-12:2023.05.1
     resource_class: gpu.nvidia.large
     parallelism: 4
     steps:
@@ -922,7 +911,7 @@ jobs:
       python-version:
         type: string
     machine:
-      image: linux-cuda-11:2023.02.1
+      image: linux-cuda-12:2023.05.1
     resource_class: gpu.nvidia.large
     steps:
       - checkout
@@ -956,7 +945,7 @@ jobs:
         type: string
     parallelism: 8
     machine:
-      image: linux-cuda-11:2023.02.1
+      image: linux-cuda-12:2023.05.1
     resource_class: gpu.nvidia.large
     steps:
       - checkout
@@ -992,7 +981,7 @@ jobs:
         type: string
     parallelism: 8
     machine:
-      image: linux-cuda-11:2023.02.1
+      image: linux-cuda-12:2023.05.1
     resource_class: gpu.nvidia.large
     steps:
       - checkout
@@ -1030,7 +1019,7 @@ jobs:
       python-version:
         type: string
     machine:
-      image: linux-cuda-11:2023.02.1
+      image: linux-cuda-12:2023.05.1
     resource_class: gpu.nvidia.large
     steps:
       - checkout
@@ -1068,7 +1057,7 @@ jobs:
         type: string
     parallelism: 4
     machine:
-      image: linux-cuda-11:2023.02.1
+      image: linux-cuda-12:2023.05.1
     resource_class: gpu.nvidia.small
     steps:
       - when:
@@ -1116,7 +1105,7 @@ jobs:
       torch-build-index:
         type: string
     machine:
-      image: linux-cuda-11:2023.02.1
+      image: linux-cuda-12:2023.05.1
     resource_class: gpu.nvidia.small
     steps:
       - when:
@@ -1252,7 +1241,7 @@ jobs:
       python-version:
         type: string
     machine:
-      image: linux-cuda-11:2023.02.1
+      image: linux-cuda-12:2023.05.1
     resource_class: gpu.nvidia.small
     steps:
       - checkout
@@ -1288,7 +1277,7 @@ jobs:
       torch-base-image:
         type: string
     machine:
-      image: linux-cuda-11:2023.02.1
+      image: linux-cuda-12:2023.05.1
     resource_class: gpu.nvidia.small
     steps:
       - checkout
@@ -1316,7 +1305,7 @@ jobs:
       torch-base-image:
         type: string
     machine:
-      image: linux-cuda-11:2023.02.1
+      image: linux-cuda-12:2023.05.1
     resource_class: gpu.nvidia.small
     steps:
       - when:
@@ -1352,13 +1341,13 @@ parameters:
   # Nightly platform config
   torch-build:
     type: string
-    default: "2.1.0.dev20230605+cu118"
+    default: "2.1.0.dev20230613+cu121"
   torchvision-build:
     type: string
-    default: "0.16.0.dev20230605+cu118"
+    default: "0.16.0.dev20230613+cu121"
   torch-build-index:
     type: string
-    default: "https://download.pytorch.org/whl/nightly/cu118"
+    default: "https://download.pytorch.org/whl/nightly/cu121"
   torch-build-legacy:
     type: string
     default: "1.13.1+cu117"
@@ -1373,7 +1362,7 @@ parameters:
     default: true
   cudnn-version:
     type: string
-    default: "8.8.0.121"
+    default: "8.9.1.23"
   trt-version-short:
     type: string
     default: "8.6.1"

diff --git a/README.md b/README.md
@@ -116,9 +116,9 @@ torch.jit.save(trt_ts_module, "trt_torchscript_module.ts") # save the TRT embedd
 These are the following dependencies used to verify the testcases. Torch-TensorRT can work with other versions, but the tests are not guaranteed to pass.
 
 - Bazel 5.2.0
-- Libtorch 2.1.0.dev20230605 (built with CUDA 11.8)
-- CUDA 11.8
-- cuDNN 8.8.0
+- Libtorch 2.1.0.dev20230613 (built with CUDA 12.1)
+- CUDA 12.1
+- cuDNN 8.9.1
 - TensorRT 8.6.1
 
 ## Prebuilt Binaries and Wheel files

diff --git a/WORKSPACE b/WORKSPACE
@@ -41,7 +41,7 @@ local_repository(
 new_local_repository(
     name = "cuda",
     build_file = "@//third_party/cuda:BUILD",
-    path = "/usr/local/cuda-11.8/",
+    path = "/usr/local/cuda-12.1/",
 )
 
 #############################################################################################################
@@ -51,17 +51,17 @@ new_local_repository(
 http_archive(
     name = "libtorch",
     build_file = "@//third_party/libtorch:BUILD",
-    sha256 = "999becce82b73e566d0ffe010cd21fea8cf3a33f90f09dcc6b01150b820ae063",
+    sha256 = "1c3712b3b1de34e9989549f53675b557f6f0ca0b800ccbbc80c941af68abcc65",
     strip_prefix = "libtorch",
-    urls = ["https://download.pytorch.org/libtorch/nightly/cu118/libtorch-cxx11-abi-shared-with-deps-2.1.0.dev20230605%2Bcu118.zip"],
+    urls = ["https://download.pytorch.org/libtorch/nightly/cu121/libtorch-cxx11-abi-shared-with-deps-2.1.0.dev20230613%2Bcu121.zip"],
 )
 
 http_archive(
     name = "libtorch_pre_cxx11_abi",
     build_file = "@//third_party/libtorch:BUILD",
-    sha256 = "786cc728c63ea69c40bd8fb535cf8e5e1dfff1d43eaad3eb5256b9ed89c1b268",
+    sha256 = "6bbb53f2f9533804175a0d2eeae5093ee1907158a9ec75c7fb9d10e2103d5df5",
     strip_prefix = "libtorch",
-    urls = ["https://download.pytorch.org/libtorch/nightly/cu118/libtorch-shared-with-deps-2.1.0.dev20230605%2Bcu118.zip"],
+    urls = ["https://download.pytorch.org/libtorch/nightly/cu121/libtorch-shared-with-deps-2.1.0.dev20230613%2Bcu121.zip"],
 )
 
 # Download these tarballs manually from the NVIDIA website
@@ -71,20 +71,20 @@ http_archive(
 http_archive(
     name = "cudnn",
     build_file = "@//third_party/cudnn/archive:BUILD",
-    sha256 = "36fff137153ef73e6ee10bfb07f4381240a86fb9fb78ce372414b528cbab2293",
-    strip_prefix = "cudnn-linux-x86_64-8.8.0.121_cuda11-archive",
+    sha256 = "35163c5c542be0c511738b27e25235193cbeedc5e0e006e44b1cdeaf1922e83e",
+    strip_prefix = "cudnn-linux-x86_64-8.9.1.23_cuda12-archive",
     urls = [
-        "https://developer.download.nvidia.com/compute/cudnn/secure/8.8.0/local_installers/11.8/cudnn-linux-x86_64-8.8.0.121_cuda11-archive.tar.xz",
+        "https://developer.nvidia.com/downloads/compute/cudnn/secure/8.9.1/local_installers/12.x/cudnn-linux-x86_64-8.9.1.23_cuda12-archive.tar.xz",
     ],
 )
 
 http_archive(
     name = "tensorrt",
     build_file = "@//third_party/tensorrt/archive:BUILD",
-    sha256 = "15bfe6053d45feec45ecc7123a9106076b0b43fa0435f242d89dca0778337759",
+    sha256 = "0f8157a5fc5329943b338b893591373350afa90ca81239cdadd7580cd1eba254",
     strip_prefix = "TensorRT-8.6.1.6",
     urls = [
-        "https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/secure/8.6.1/tars/TensorRT-8.6.1.6.Linux.x86_64-gnu.cuda-11.8.tar.gz",
+        "https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/secure/8.6.1/tars/TensorRT-8.6.1.6.Linux.x86_64-gnu.cuda-12.0.tar.gz",
     ],
 )
 

diff --git a/docker/Dockerfile b/docker/Dockerfile
@@ -1,7 +1,7 @@
 # Base image starts with CUDA
-ARG BASE_IMG=nvidia/cuda:11.8.0-devel-ubuntu22.04
+ARG BASE_IMG=nvidia/cuda:12.1.1-devel-ubuntu22.04
 FROM ${BASE_IMG} as base
-ENV BASE_IMG=nvidia/cuda:11.8.0-devel-ubuntu22.04
+ENV BASE_IMG=nvidia/cuda:12.1.1-devel-ubuntu22.04
 
 ARG TENSORRT_VERSION
 ENV TENSORRT_VERSION=${TENSORRT_VERSION}