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
Torch-TensorRT is also distributed in the ready-to-run [NVIDIA NGC PyTorch Container](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/pytorch) which has all dependencies with the proper versions and example notebooks included.
If you use the ``uv`` (`https://docs.astral.sh/uv/ <https://docs.astral.sh/uv/>`_) tool to manage python and your projects, the command is slightly simpler
Building the C++ Library Standalone (TorchScript Only)
@@ -245,7 +245,7 @@ Build steps
245
245
246
246
* Open the app "x64 Native Tools Command Prompt for VS 2022" - note that Admin privileges may be necessary
247
247
* Ensure Bazelisk (Bazel launcher) is installed on your machine and available from the command line. Package installers such as Chocolatey can be used to install Bazelisk
248
-
* Install latest version of Torch (i.e. with ``pip install --pre torch --index-url https://download.pytorch.org/whl/nightly/cu128``)
248
+
* Install latest version of Torch (i.e. with ``pip install --pre torch --index-url https://download.pytorch.org/whl/nightly/cu130``)
249
249
* Clone the Torch-TensorRT repository and navigate to its root directory
250
250
* Run ``pip install ninja wheel setuptools``
251
251
* Run ``pip install --pre -r py/requirements.txt``
0 commit comments