You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docker/README.md
+3-2Lines changed: 3 additions & 2 deletions
Original file line number
Diff line number
Diff line change
@@ -5,7 +5,8 @@
5
5
*`Dockerfile` currently uses the exact library versions (Torch, CUDA, CUDNN, TensorRT) listed in <ahref="https://github.com/pytorch/TensorRT#dependencies">dependencies</a> to build Torch-TensorRT.
6
6
7
7
* This `Dockerfile` installs `pre-cxx11-abi` versions of Pytorch and builds Torch-TRT using `pre-cxx11-abi` libtorch as well.
8
-
Note: To install `cxx11_abi` version of Torch-TensorRT, enable `USE_CXX11=1` flag so that `dist-build.sh` can build it accordingly.
8
+
9
+
Note: By default the container uses the `pre-cxx11-abi` version of Torch + Torch-TRT. If you are using a workflow that requires a build of PyTorch on the CXX11 ABI (e.g. using the PyTorch NGC containers as a base image), add the Docker build argument: `--build-arg USE_CXX11_ABI=1`
9
10
10
11
### Dependencies
11
12
@@ -38,4 +39,4 @@ bazel test //tests/core/conversion/converters:test_activation --compilation_mode
38
39
39
40
### Pytorch NGC containers
40
41
41
-
We also ship Torch-TensorRT in <ahref="https://catalog.ngc.nvidia.com/orgs/nvidia/containers/pytorch">Pytorch NGC containers </a>. Release notes for these containers can be found <ahref="https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/index.html">here</a>. Check out `release/ngc/23.XX` branch of Torch-TensorRT for source code that gets shipped with `23.XX` version of Pytorch NGC container.
42
+
We also ship Torch-TensorRT in <ahref="https://catalog.ngc.nvidia.com/orgs/nvidia/containers/pytorch">Pytorch NGC containers </a>. Release notes for these containers can be found <ahref="https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/index.html">here</a>. Check out `release/ngc/23.XX` branch of Torch-TensorRT for source code that gets shipped with `23.XX` version of Pytorch NGC container.
0 commit comments