From 3f400352d791519a40563ca1721112bf915820dd Mon Sep 17 00:00:00 2001 From: Yuwen Hu Date: Wed, 27 Mar 2024 18:08:26 +0800 Subject: [PATCH 1/2] Hide oneAPI install with pip installer for now --- .../source/doc/LLM/Overview/install_gpu.md | 21 ++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/docs/readthedocs/source/doc/LLM/Overview/install_gpu.md b/docs/readthedocs/source/doc/LLM/Overview/install_gpu.md index b46f39c2fe8..2256d5564bd 100644 --- a/docs/readthedocs/source/doc/LLM/Overview/install_gpu.md +++ b/docs/readthedocs/source/doc/LLM/Overview/install_gpu.md @@ -20,7 +20,11 @@ To apply Intel GPU acceleration, there're several prerequisite steps for tools i * Step 3: Install Intel® oneAPI Base Toolkit 2024.0 -Intel® oneAPI Base Toolkit 2024.0 installation methods: + Download and install `Intel® oneAPI Base Toolkit `_ version 2024.0 through Offline Installer. + + During installation, you could just continue with "Recommended Installation". If you would like to continue with "Custom Installation", please note that oneAPI Deep Neural Network Library, oneAPI Math Kernel Library, and oneAPI DPC++/C++ Compiler are required, the other components are optional. + + ### Install IPEX-LLM From PyPI @@ -91,7 +95,9 @@ pip install --pre --upgrade ipex-llm[xpu] To use GPU acceleration on Windows, several environment variables are required before running a GPU example. -Make sure you are using CMD (Anaconda Prompt if using conda) as PowerShell is not supported. For oneAPI installed using the Offline installer, configure oneAPI environment variables with: + + +Make sure you are using CMD (Anaconda Prompt if using conda) as PowerShell is not supported, and configure oneAPI environment variables with: ```cmd call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" @@ -143,13 +149,18 @@ If you met error when importing `intel_extension_for_pytorch`, please ensure tha ```cmd conda install libuv ``` - -* For oneAPI installed using the Offline installer, make sure you have configured oneAPI environment variables in your Anaconda Prompt through +* Make sure you have configured oneAPI environment variables in your Anaconda Prompt through ```cmd call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" ``` Please note that you need to set these environment variables again once you have a new Anaconda Prompt window. + + ## Linux ### Prerequisites From 883105c9cb0329f8664bf1c1b313ee815eaa9a48 Mon Sep 17 00:00:00 2001 From: Yuwen Hu Date: Wed, 27 Mar 2024 18:12:39 +0800 Subject: [PATCH 2/2] Small fix --- docs/readthedocs/source/doc/LLM/Overview/install_gpu.md | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/docs/readthedocs/source/doc/LLM/Overview/install_gpu.md b/docs/readthedocs/source/doc/LLM/Overview/install_gpu.md index 2256d5564bd..138cf845d3e 100644 --- a/docs/readthedocs/source/doc/LLM/Overview/install_gpu.md +++ b/docs/readthedocs/source/doc/LLM/Overview/install_gpu.md @@ -18,9 +18,7 @@ To apply Intel GPU acceleration, there're several prerequisite steps for tools i * Step 2: Install or update to latest [GPU driver](https://www.intel.com/content/www/us/en/download/785597/intel-arc-iris-xe-graphics-windows.html) -* Step 3: Install Intel® oneAPI Base Toolkit 2024.0 - - Download and install `Intel® oneAPI Base Toolkit `_ version 2024.0 through Offline Installer. +* Step 3: Install Intel® oneAPI Base Toolkit 2024.0: download and install [Intel® oneAPI Base Toolkit](https://www.intel.com/content/www/us/en/developer/tools/oneapi/base-toolkit-download.html?operatingsystem=window&distributions=offline>) version 2024.0 through Offline Installer. During installation, you could just continue with "Recommended Installation". If you would like to continue with "Custom Installation", please note that oneAPI Deep Neural Network Library, oneAPI Math Kernel Library, and oneAPI DPC++/C++ Compiler are required, the other components are optional.