diff --git a/.wordlist.txt b/.wordlist.txt index 8b484d7e..68eff792 100644 --- a/.wordlist.txt +++ b/.wordlist.txt @@ -70,7 +70,6 @@ SMCi SRIOV SVM SuperMicro -Taichi tbody td thead diff --git a/docs/index.rst b/docs/index.rst index 6ffbbfe3..f8cab3ee 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -33,7 +33,6 @@ This section describes the ROCm for Linux installation options. * :doc:`Stanford Megatron-LM ` * :doc:`DGL ` * :doc:`Megablocks ` - * :doc:`Taichi ` * :doc:`Ray ` * :doc:`llama.cpp ` * :doc:`FlashInfer ` diff --git a/docs/install/3rd-party/jax-install.rst b/docs/install/3rd-party/jax-install.rst index 7833d6ab..e9f2763e 100644 --- a/docs/install/3rd-party/jax-install.rst +++ b/docs/install/3rd-party/jax-install.rst @@ -112,11 +112,11 @@ If you prefer to use the ROCm Ubuntu image or already have a ROCm Ubuntu contain :sync: python-3.10 :selected: - .. code-block:: bash pip install https://github.com/ROCm/rocm-jax/releases/download/rocm-jax-v0.6.0/jaxlib-0.6.0-cp310-cp310-manylinux2014_x86_64.whl + 4. Install JAX, ``jax-rocm7-pjrt``, and ``jax-rocm7-plugin`` from PyPI. .. code-block:: bash @@ -236,6 +236,7 @@ Follow these steps if you prefer to install ROCm manually on your host system or pip install https://github.com/ROCm/rocm-jax/releases/download/rocm-jax-v0.6.0/jaxlib-0.6.0-cp313-cp313-manylinux2014_x86_64.whl + .. tab-item:: Python 3.12 :sync: python-3.12 @@ -243,6 +244,7 @@ Follow these steps if you prefer to install ROCm manually on your host system or pip install https://github.com/ROCm/rocm-jax/releases/download/rocm-jax-v0.6.0/jaxlib-0.6.0-cp312-cp312-manylinux2014_x86_64.whl + .. tab-item:: Python 3.11 :sync: python-3.11 @@ -250,14 +252,16 @@ Follow these steps if you prefer to install ROCm manually on your host system or pip install https://github.com/ROCm/rocm-jax/releases/download/rocm-jax-v0.6.0/jaxlib-0.6.0-cp311-cp311-manylinux2014_x86_64.whl + .. tab-item:: Python 3.10 :sync: python-3.10 - :selected + :selected: .. code-block:: bash pip install https://github.com/ROCm/rocm-jax/releases/download/rocm-jax-v0.6.0/jaxlib-0.6.0-cp310-cp310-manylinux2014_x86_64.whl + 4. Install JAX, ``jax-rocm7-pjrt``, and ``jax-rocm7-plugin`` from PyPI. .. code-block:: bash diff --git a/docs/install/3rd-party/previous-versions/llama-cpp-install-v25.8.rst b/docs/install/3rd-party/previous-versions/llama-cpp-install-v25.8.rst index eb1bec9a..e8a2dbb3 100644 --- a/docs/install/3rd-party/previous-versions/llama-cpp-install-v25.8.rst +++ b/docs/install/3rd-party/previous-versions/llama-cpp-install-v25.8.rst @@ -28,10 +28,10 @@ Install llama.cpp To install llama.cpp for ROCm, you have the following options: -* :ref:`using-docker-with-llama-cpp-pre-installed` **(recommended)** -* :ref:`build-llama-cpp-docker-image` +* :ref:`using-docker-with-llama-cpp-pre-installed-v25-8` **(recommended)** +* :ref:`build-llama-cpp-docker-image-v25-8` -.. _using-docker-with-llama-cpp-pre-installed: +.. _using-docker-with-llama-cpp-pre-installed-v25-8: Use a prebuilt Docker image with llama.cpp pre-installed -------------------------------------------------------------------------------------- @@ -51,7 +51,7 @@ and other dependencies. - Light: This image only includes the main executable file. You can download Docker images with specific ROCm, llama.cpp, and operating system versions. - See the available tags on `Docker Hub `_ and see :ref:`docker image support ` below. + See the available tags on `Docker Hub `_ and see :ref:`docker image support ` below. 1. Download your required public `llama.cpp Docker image `__: @@ -117,7 +117,7 @@ and other dependencies. This will automatically download the image if it does not exist on the host. You can also pass the ``-v`` argument to mount any data directories from the host onto the container. -.. _llama-cpp-docker-support: +.. _llama-cpp-docker-support-v25-8: Docker image support -------------------------------------------------------------------------------------- @@ -165,7 +165,7 @@ validated for `ROCm 6.4.0 `_. * `ROCm 6.4.0 `_ -.. _build-llama-cpp-docker-image: +.. _build-llama-cpp-docker-image-v25-8: Build your own Docker image -------------------------------------------------------------------------------------- @@ -246,7 +246,7 @@ prebuilt Docker image from AMD ROCm Docker Hub. To run unit tests manually and validate your installation fully, follow these steps: -1. To verify that llama.cpp has been successfully installed, run the Docker container as described in :ref:`build-llama-cpp-docker-image`. +1. To verify that llama.cpp has been successfully installed, run the Docker container as described in :ref:`build-llama-cpp-docker-image-v25-8`. 2. Once inside the container, ensure you have access to the Bash shell. diff --git a/docs/install/3rd-party/taichi-install.rst b/docs/install/3rd-party/taichi-install.rst deleted file mode 100644 index 9616883f..00000000 --- a/docs/install/3rd-party/taichi-install.rst +++ /dev/null @@ -1,202 +0,0 @@ -.. meta:: - :description: Install Taichi on ROCm - :keywords: installation, docker, Taichi, AMD, ROCm - -******************************************************************************** -Taichi on ROCm -******************************************************************************** - -`Taichi `_ is an open-source, imperative, and parallel -programming language designed for high-performance numerical computation. -Embedded in Python, it leverages just-in-time (JIT) compilation frameworks such as LLVM to accelerate -compute-intensive Python code by compiling it to native GPU or CPU instructions. - -For hardware, software, and third-party framework compatibility between ROCm and Taichi, -see the following resources: - -* :ref:`system-requirements` -* :doc:`rocm:compatibility/ml-compatibility/taichi-compatibility` - -.. note:: - - Taichi is supported on ROCm 6.3.2. - -Install Taichi -================================================================================ - -To install Taichi on ROCm, you have the following options: - -- :ref:`Use the prebuilt Docker image ` **(recommended)** -- :ref:`Use a wheels package ` -- :ref:`Build your own docker image ` - -.. _using-docker-with-taichi-pre-installed: - -Use a prebuilt Docker image with Taichi pre-installed --------------------------------------------------------------------------------- - -Docker is the recommended method to set up a Taichi environment, and it avoids potential installation issues. -The tested, prebuilt image includes Taichi, Python, ROCm, and other dependencies. - -1. Pull the Docker image - - .. code-block:: bash - - docker pull rocm/taichi:taichi-1.8.0b1_rocm6.3.2_ubuntu22.04_py3.10.12 - -2. Launch and connect to the container - - .. code-block:: bash - - docker run -it -d --network=host --device=/dev/kfd --device=/dev/dri --ipc=host --shm-size 64G \ - --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v $(pwd):/taichi_dir \ - --name rocm_taichi rocm/taichi:taichi-1.8.0b1_rocm6.3.2_ubuntu22.04_py3.10.12 - -.. _taichi-wheels-package: - -Use a wheels package --------------------------------------------------------------------------------- - -The Taichi ``.whl`` packages are hosted on the AMD PyPI repository. -Instead of manually downloading the files, you can simply install Taichi using ``pip`` with the provided URL. -This command will automatically download and install the appropriate ``.whl`` file. - -.. code-block:: bash - - pip install amd-taichi==1.8.0b1 --extra-index-url=https://pypi.amd.com/simple - sudo apt-get update - sudo apt-get install -y lld - -.. _build-taichi-rocm-docker-image: - -Build your own Docker image --------------------------------------------------------------------------------- - -If you prefer to use the ROCm Ubuntu image, or already have a ROCm Ubuntu container, follow these steps to install Taichi in the container. - -1. Pull the ROCm Ubuntu Docker image - - .. code-block:: bash - - docker pull rocm/dev-ubuntu-22.04:6.3.2 - -2. Launch the Docker container - - .. code-block:: bash - - docker run -it -d --network=host --device=/dev/kfd --device=/dev/dri --ipc=host --shm-size 64G \ - --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v $(pwd):/taichi_dir \ - --name rocm_taichi rocm/dev-ubuntu-22.04:6.3.2 /bin/bash - -3. Inside the running container, install build dependencies - - .. code-block:: bash - - sudo apt-get update && apt-get install -y --no-install-recommends \ - git wget vim \ - freeglut3-dev libglfw3-dev libglm-dev libglu1-mesa-dev \ - libjpeg-dev liblz4-dev libpng-dev libssl-dev \ - libwayland-dev libx11-xcb-dev libxcb-dri3-dev libxcb-ewmh-dev \ - libxcb-keysyms1-dev libxcb-randr0-dev libxcursor-dev libxi-dev \ - libxinerama-dev libxrandr-dev libzstd-dev \ - python3-pip cmake pybind11-dev ca-certificates \ - llvm-15 clang-15 lld-15 \ - && apt-get clean && rm -rf /var/lib/apt/lists/* - -4. Add LLVM 15 to PATH - - .. code-block:: bash - - export LLVM_DIR=/usr/lib/llvm-15 - export PATH=${LLVM_DIR}/bin:$PATH - -5. Clone the `https://github.com/ROCm/taichi `_ repository with the desired branch - - .. code-block:: bash - - cd - git clone --recursive https://github.com/ROCm/taichi -b amd-release/v1.8.0b1 - cd taichi - -6. Build the Taichi wheel - - .. code-block:: bash - - export GPU_TARGETS=gfx90a - export TAICHI_CMAKE_ARGS="-DTI_WITH_VULKAN=OFF -DTI_WITH_OPENGL=OFF -DTI_BUILD_TESTS=ON -DTI_BUILD_EXAMPLES=OFF -DCMAKE_PREFIX_PATH=${LLVM_DIR}/lib/cmake -DCMAKE_CXX_COMPILER=${LLVM_DIR}/bin/clang++ -DTI_WITH_AMDGPU=ON -DTI_WITH_CUDA=OFF -DTI_AMDGPU_ARCHS=${GPU_TARGETS}" - - ./build.py - -7. Install the Taichi ``.whl`` file - - .. code-block:: bash - - pip3 install /dist/taichi*.whl - - -.. _build-taichi-docker-from-source: - -Test the Taichi installation -================================================================================ - -Clone the `https://github.com/ROCm/taichi `_ repository - - .. code-block:: bash - - sudo apt-get update - sudo apt-get install -y git - git clone --recursive https://github.com/ROCm/taichi -b amd-release/v1.8.0b1 - -To test the Taichi installation, run the ``laplace`` example in the source code: - -.. code-block:: bash - - python3 taichi/python/taichi/examples/algorithm/laplace.py - - -``laplace`` example output: - -.. code-block:: bash - - [Taichi] version 1.8.0, llvm 15.0.0, commit f7911653, linux, python 3.10.12 - [Taichi] Starting on arch=amdgpu - 0.0 - 4.0 - 0.0 - 0.0 - 4.0 - 0.0 - 0.0 - 4.0 - 0.0 - 0.0 - - -Run a Taichi example -================================================================================ - -Several examples have been collected in the `https://github.com/ROCm/taichi_examples `_ repository. -This repository contains a Dockerfile for building a container and installing Taichi. It contains a ``README.md`` file that guides the building of the container using the Dockerfile and running the examples. - -1. Clone the repository: - - .. code-block:: bash - - git clone https://github.com/ROCm/taichi_examples.git - -2. If you have Taichi installed in your environment, you do not need to build an additional container. Simply install the example dependencies: - - .. code-block:: bash - - pip3 install pillow - pip3 install --no-cache-dir torch --index-url https://download.pytorch.org/whl/nightly/rocm6.3/ - -3. Run the examples scripts from the ``taichi_examples`` directory: - - .. code-block:: bash - - cd taichi_examples - ./run_demos.sh - ./run_algorithm_graph_examples.sh - -Refer to the `AMD ROCm blog `_ to search for Taichi examples and best practices to optimize your workflows on AMD GPUs. diff --git a/docs/sphinx/_toc.yml.in b/docs/sphinx/_toc.yml.in index 8266284b..e2cb8fe4 100644 --- a/docs/sphinx/_toc.yml.in +++ b/docs/sphinx/_toc.yml.in @@ -74,8 +74,6 @@ subtrees: title: DGL - file: install/3rd-party/megablocks-install title: Megablocks - - file: install/3rd-party/taichi-install - title: Taichi - file: install/3rd-party/ray-install title: Ray - file: install/3rd-party/llama-cpp-install