ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

Update gpu pip install oneapi doc (#10137)

Browse source 
* fix link

* fix

* fix

* minor
This commit is contained in:
Kai Huang 2024-02-09 11:27:40 +08:00 committed by GitHub
parent b7c5104d98
commit 7400401706
1 changed files with 21 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

37
docs/readthedocs/source/doc/LLM/Overview/install_gpu.md
View file

@ -134,7 +134,7 @@ If you met error when importing `intel_extension_for_pytorch`, please ensure tha
### Prerequisites
BigDL-LLM for GPU supports on Linux has been verified on:
BigDL-LLM GPU support on Linux has been verified on:
* Intel Arc™ A-Series Graphics
* Intel Data Center GPU Flex Series
@ -185,19 +185,20 @@ BigDL-LLM for GPU supports on Linux has been verified on:
The oneAPI packages are visible in ``pip list`` only if ``PYTHONUSERBASE`` is properly set.
Step 2: Configure your working conda environment (e.g. with name ``llm``) to append ~/intel/oneapi/lib to environment variable LD_LIBRARY_PATH
Step 2: Configure your working conda environment (e.g. with name ``llm``) to append oneAPI path (e.g. ``~/intel/oneapi/lib``) to the environment variable ``LD_LIBRARY_PATH``.
.. code-block:: bash
conda env config vars set LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/intel/oneapi/lib -n llm
.. note::
You can view the configured environment variables for ``llm`` by running ``conda env config vars list -n llm``.
You can continue with activating the conda environment ``llm`` and installing ``bigdl-llm``.
You can view the configured environment variables for your environment (e.g. with name ``llm``) by running ``conda env config vars list -n llm``.
You can continue with your working conda environment and install ``bigdl-llm`` as guided in the next section.
.. note::
You can uninstall the package by simply deleting the package folder, and unsetting the configuration of your working conda environment (e.g., with name ``llm``). Thus, you are recommended to not install other pip packages in this folder.
You are recommended not to install other pip packages in the user-defined folder for oneAPI (e.g. ``~/intel/oneapi``).
You can uninstall the oneAPI package by simply deleting the package folder, and unsetting the configuration of your working conda environment (e.g., with name ``llm``).
.. code-block:: bash
@ -277,19 +278,20 @@ BigDL-LLM for GPU supports on Linux has been verified on:
The oneAPI packages are visible in ``pip list`` only if ``PYTHONUSERBASE`` is properly set.
Step 2: Configure your working conda environment (e.g. with name ``llm``) to append ~/intel/oneapi/lib to environment variable LD_LIBRARY_PATH
Step 2: Configure your working conda environment (e.g. with name ``llm``) to append oneAPI path (e.g. ``~/intel/oneapi/lib``) to the environment variable ``LD_LIBRARY_PATH``.
.. code-block:: bash
conda env config vars set LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/intel/oneapi/lib -n llm
.. note::
You can view the configured environment variables for ``llm`` by running ``conda env config vars list -n llm``.
You can continue with activating the conda environment ``llm`` and installing ``bigdl-llm``.
You can view the configured environment variables for your environment (e.g. with name ``llm``) by running ``conda env config vars list -n llm``.
You can continue with your working conda environment and install ``bigdl-llm`` as guided in the next section.
.. note::
You can uninstall the package by simply deleting the package folder, and unsetting the configuration of your working conda environment (e.g., with name ``llm``). Thus, you are recommended to not install other pip packages in this folder.
You are recommended not to install other pip packages in the user-defined folder for oneAPI (e.g. ``~/intel/oneapi``).
You can uninstall the oneAPI package by simply deleting the package folder, and unsetting the configuration of your working conda environment (e.g., with name ``llm``).
.. code-block:: bash
@ -461,10 +463,11 @@ To use GPU acceleration on Linux, several environment variables are required or
.. code-block:: bash
# Required step for APT or offline installed oneAPI. Configure oneAPI environment variables. Skip this step for pip-installed oneAPI since LD_LIBRARY_PATH has already been configured.
# Configure oneAPI environment variables. Required step for APT or offline installed oneAPI.
# Skip this step for PIP-installed oneAPI since the environment has already been configured in LD_LIBRARY_PATH.
source /opt/intel/oneapi/setvars.sh
# Recommended Environment Variables
# Recommended Environment Variables for optimal performance
export USE_XETLA=OFF
export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1
@ -474,9 +477,11 @@ To use GPU acceleration on Linux, several environment variables are required or
.. code-block:: bash
# Required step for APT or offline installed oneAPI. Configure oneAPI environment variables. Skip this step for pip-installed oneAPI since LD_LIBRARY_PATH has already been configured.
# Configure oneAPI environment variables. Required step for APT or offline installed oneAPI.
# Skip this step for PIP-installed oneAPI since the environment has already been configured in LD_LIBRARY_PATH.
source /opt/intel/oneapi/setvars.sh
# Recommended Environment Variables
# Recommended Environment Variables for optimal performance
export LD_PRELOAD=${LD_PRELOAD}:${CONDA_PREFIX}/lib/libtcmalloc.so
export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1
export ENABLE_SDP_FUSION=1
@ -520,6 +525,6 @@ Error: libmkl_sycl_blas.so.4: cannot open shared object file: No such file or di
The reason for such errors is that oneAPI has not been initialized properly before running BigDL-LLM code or before importing IPEX package.
* Step 1: For oneAPI installed using APT or Offline Installer, make sure you execute setvars.sh of oneAPI Base Toolkit before running BigDL-LLM code.
For PIP-installed oneAPI, run ``echo $LD_LIBRARY_PATH``. If the output does not contain ``<oneAPI_folder>/lib``, check `Prerequisites`_. to install oneAPI with PIP installer again
* Step 2: Make sure you install matching versions of BigDL-LLM/pytorch/IPEX and oneAPI Base Toolkit. BigDL-LLM with PyTorch 2.1 should be used with oneAPI Base Toolkit version 2024.0. BigDL-LLM with PyTorch 2.0 should be used with oneAPI Base Toolkit version 2023.2.
* For oneAPI installed using APT or Offline Installer, make sure you execute `setvars.sh` of oneAPI Base Toolkit before running BigDL-LLM.
* For PIP-installed oneAPI, run ``echo $LD_LIBRARY_PATH`` to check if the installation path is properly configured. If the output does not contain oneAPI path (e.g. ``~/intel/oneapi/lib``), check [Prerequisites](#id1) to re-install oneAPI with PIP installer.
* Make sure you install matching versions of BigDL-LLM/pytorch/IPEX and oneAPI Base Toolkit. BigDL-LLM with PyTorch 2.1 should be used with oneAPI Base Toolkit version 2024.0. BigDL-LLM with PyTorch 2.0 should be used with oneAPI Base Toolkit version 2023.2.