From 9282e66626a8bcc2667dbf8a4649e6f46597d70b Mon Sep 17 00:00:00 2001
From: natke <nakersha@microsoft.com>
Date: Tue, 6 Aug 2024 16:44:10 -0700
Subject: [PATCH] Update install instructions for separate packages

---
 docs/genai/howto/install.md | 88 ++++++++++++++++++++++++++++++++-----
 1 file changed, 76 insertions(+), 12 deletions(-)

diff --git a/docs/genai/howto/install.md b/docs/genai/howto/install.md
index c77a9e089cc0b..3a2eee75a7afb 100644
--- a/docs/genai/howto/install.md
+++ b/docs/genai/howto/install.md
@@ -15,6 +15,10 @@ nav_order: 1
 
 ## Pre-requisites
 
+### ONNX Runtime
+
+Previous versions of ONNX Runtime generate() came bundled with the core ONNX Runtime binaries. From version 0.4.0 onwards, the packages are separated to allow a better developer experience. Specific platform instructions are included in each section below.
+
 ### CUDA
 
 If you are installing the CUDA variant of onnxruntime-genai, the CUDA toolkit must be installed.
@@ -23,61 +27,121 @@ The CUDA toolkit can be downloaded from the [CUDA Toolkit Archive](https://devel
 
 Ensure that the `CUDA_PATH` environment variable is set to the location of your CUDA installation.
 
+Versions later than ONNX Runtime release bundle CUDA 12 by default. CUDA 11 is also supported in a separate package. Instructions are given below.
+
 ## Python packages
 
-Note: only one of these packages should be installed in your application.
+Note: only one of these set of packages (CPU, DirectML, CUDA) should be installed in your environment.
 
 ### CPU
 
+#### Intel CPU
+
 ```bash
-pip install numpy
+pip install onnxruntime
+pip install onnxruntime-genai --pre
+```
+
+#### Arm CPU
+
+```bash
+pip install onnxruntime-qnn
 pip install onnxruntime-genai --pre
 ```
 
-### DirectML
 
-Append `-directml` for the library that is optimized for DirectML on Windows
+### DirectML
 
 ```bash
 pip install numpy
+pip install onnxruntime-directml
 pip install onnxruntime-genai-directml --pre
 ```
 
 ### CUDA
 
-Append `-cuda` for the library that is optimized for CUDA environments
-
 #### CUDA 11
 
 ```bash
-pip install numpy
-pip install onnxruntime-genai-cuda --pre --index-url=https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-genai/pypi/simple/
+# Install ORT nightly CUDA 11, change this to released version when it is released
+pip install ort-nightly-gpu --index-url
+https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/ort-cuda-11-nightly/pypi/simple
+
+
+# Install onnxruntime-genai built for CUDA 11
+pip install onnxruntime-genai-cuda-11 --pre --index-url=https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-genai/pypi/simple/
 ```
 
 #### CUDA 12
 
 ```bash
-pip install numpy
-pip install onnxruntime-genai-cuda --pre --index-url=https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-12/pypi/simple/
+# Install ORT nightly CUDA 12, change this to released version when it is released
+pip install onnxruntime-gpu --extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-12/pypi/simple/
+
+# Install onnxruntime-genai build for CUDA 12
+pip install onnxruntime-genai-cuda --pre --index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-genai/pypi/simple/
 ```
 
 ## Nuget packages
 
-Note: only one of these packages should be installed in your application.
+Note: only one of these set of packages (CPU, DirectML, CUDA) should be installed in your application.
+
+### CPU
 
 ```bash
+dotnet add package Microsoft.ML.OnnxRuntime
 dotnet add package Microsoft.ML.OnnxRuntimeGenAI --prerelease
 ```
 
-For the package that has been optimized for CUDA:
+### CUDA 
+
+#### CUDA 11
+
+Add the following lines to a `nuget.config` file in the same folder as your `.csproj` file.
+
+```xml
+<?xml version="1.0" encoding="utf-8"?>
+<configuration>
+    <packageSources>
+        <clear/>
+        <add key="onnxruntime-cuda-11"
+             value="https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-11/nuget/v3/index.json"/>
+    </packageSources>
+</configuration>
+```
 
 ```bash
+dotnet add package Microsoft.ML.OnnxRuntime.Gpu
 dotnet add package Microsoft.ML.OnnxRuntimeGenAI.Cuda --prerelease
 ```
 
+#### CUDA 12
+
+Add the following lines to a `nuget.config` file in the same folder as your `.csproj` file.
+
+```xml
+<?xml version="1.0" encoding="utf-8"?>
+<configuration>
+    <packageSources>
+        <clear/>
+        <add key="onnxruntime-cuda-12"
+             value="https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-12/nuget/v3/index.json"/>
+    </packageSources>
+</configuration>
+```
+
+
+```bash
+dotnet add package Microsoft.ML.OnnxRuntime.Gpu
+dotnet add package Microsoft.ML.OnnxRuntimeGenAI.Cuda --prerelease
+```
+
+### DirectML
+
 For the package that has been optimized for DirectML:
 
 ```bash
+dotnet add package Microsoft.ML.OnnxRuntime.DirectML
 dotnet add package Microsoft.ML.OnnxRuntimeGenAI.DirectML --prerelease
 ```