Files
pytorch/.devcontainer/scripts/install-dev-tools.sh
Xuehai Pan 42a4df9447 Support CUDA nightly package in tools/nightly.py (#131133)
Add a new option `--cuda` to `tools/nightly.py` to pull the nightly packages with CUDA support.

```bash
# installs pytorch-nightly with cpuonly
tools/nightly.py pull

# The following only available on Linux and Windows
# installs pytorch-nightly with latest CUDA we support
tools/nightly.py pull --cuda

# installs pytorch-nightly with CUDA 12.1
tools/nightly.py pull --cuda 12.1
```

Also add targets in `Makefile` and instructions in constribution guidelines.

```bash
# setup conda environment with pytorch-nightly
make setup-env

# setup conda environment with pytorch-nightly with CUDA support
make setup-env-cuda
```
Pull Request resolved: https://github.com/pytorch/pytorch/pull/131133
Approved by: https://github.com/ezyang
2024-07-25 05:33:52 +00:00

14 lines
540 B
Bash

#!/usr/bin/env bash
# Run this command from the PyTorch directory after cloning the source code using the “Get the PyTorch Source“ section below
pip install -r requirements.txt
git submodule sync
git submodule update --init --recursive
# This takes some time
make setup-lint
# Add CMAKE_PREFIX_PATH to bashrc
echo 'export CMAKE_PREFIX_PATH=${CONDA_PREFIX:-"$(dirname $(which conda))/../"}' >> ~/.bashrc
# Add linker path so that cuda-related libraries can be found
echo 'export LDFLAGS="-L${CONDA_PREFIX}/lib/ $LDFLAGS"' >> ~/.bashrc