diff --git a/docs/source/docker/intro.rst b/docs/source/docker/intro.rst index cbd300d9b..f3d2b0727 100644 --- a/docs/source/docker/intro.rst +++ b/docs/source/docker/intro.rst @@ -34,6 +34,14 @@ which will give you something like below: .. code-block:: bash + "torch2.3.1-cuda12.1" + "torch2.3.1-cuda11.8" + "torch2.2.2-cuda12.1" + "torch2.2.2-cuda11.8" + "torch2.2.1-cuda12.1" + "torch2.2.1-cuda11.8" + "torch2.2.0-cuda12.1" + "torch2.2.0-cuda11.8" "torch2.1.0-cuda12.1" "torch2.1.0-cuda11.8" "torch2.0.0-cuda11.7" diff --git a/docs/source/model-export/export-ncnn-conv-emformer.rst b/docs/source/model-export/export-ncnn-conv-emformer.rst index 93392aee7..4cdc25ee6 100644 --- a/docs/source/model-export/export-ncnn-conv-emformer.rst +++ b/docs/source/model-export/export-ncnn-conv-emformer.rst @@ -15,8 +15,8 @@ We will show you step by step how to export it to `ncnn`_ and run it with `sherp .. caution:: - Please use a more recent version of PyTorch. For instance, ``torch 1.8`` - may ``not`` work. + ``torch > 2.0`` may not work. If you get errors while building pnnx, please switch + to ``torch < 2.0``. 1. Download the pre-trained model --------------------------------- diff --git a/docs/source/model-export/export-ncnn-lstm.rst b/docs/source/model-export/export-ncnn-lstm.rst index 310c3d8e4..ccf522dec 100644 --- a/docs/source/model-export/export-ncnn-lstm.rst +++ b/docs/source/model-export/export-ncnn-lstm.rst @@ -15,8 +15,8 @@ We will show you step by step how to export it to `ncnn`_ and run it with `sherp .. caution:: - Please use a more recent version of PyTorch. For instance, ``torch 1.8`` - may ``not`` work. + ``torch > 2.0`` may not work. If you get errors while building pnnx, please switch + to ``torch < 2.0``. 1. Download the pre-trained model ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ diff --git a/docs/source/model-export/export-ncnn-zipformer.rst b/docs/source/model-export/export-ncnn-zipformer.rst index a5845b0e4..51fc6c8e5 100644 --- a/docs/source/model-export/export-ncnn-zipformer.rst +++ b/docs/source/model-export/export-ncnn-zipformer.rst @@ -15,8 +15,8 @@ We will show you step by step how to export it to `ncnn`_ and run it with `sherp .. caution:: - Please use a more recent version of PyTorch. For instance, ``torch 1.8`` - may ``not`` work. + ``torch > 2.0`` may not work. If you get errors while building pnnx, please switch + to ``torch < 2.0``. 1. Download the pre-trained model ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^