[Doc] Add install doc

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

docs/installation.md

@@ -1,22 +1,76 @@
-# Installation
+# Installation Guide
 
-### 1. Dependencies
-| Requirement  | Supported version | Recommended version | Note |
-| ------------ | ------- | ----------- | ----------- | 
-| Python | >= 3.9 | [3.10](https://www.python.org/downloads/) | Required for vllm |
-| CANN         | >= 8.0.RC2 | [8.0.RC3](https://www.hiascend.com/developer/download/community/result?module=cann&cann=8.0.0.beta1) | Required for vllm-ascend and torch-npu |
-| torch-npu    | >= 2.4.0   | [2.5.1rc1](https://gitee.com/ascend/pytorch/releases/tag/v6.0.0.alpha001-pytorch2.5.1)    | Required for vllm-ascend |
-| torch        | >= 2.4.0   | [2.5.1](https://github.com/pytorch/pytorch/releases/tag/v2.5.1)      | Required for torch-npu and vllm required |
+## Prerequisites
 
-### 2. Prepare Ascend NPU environment
+Before installing vllm-ascend, please make sure that your environment meets the following requirements:
+1. A hardware with Ascend NPU. It's usually the Atlas 800 A2 series.
+2. Linux OS. It's recommended to use openEuler 22.03 or Ubuntu 22.04.
+3. The firmware and driver for NPU is installed correctly. i.e. `npu-smi` command is available.
+4. CANN 8.0.0 or later is installed. (It's not necessary if you use the container way, since it has installed inside the image.)
 
-Below is a quick note to install recommended version software:
+> Tips: following the instructions provided in the [Ascend Installation Guide](https://ascend.github.io/docs/sources/ascend/quick_install.html) can help you to set up the environment easily.
 
-#### Containerized installation
+## Installation
 
-You can use the [container image](https://hub.docker.com/r/ascendai/cann) directly with one line command:
+After the environment is ready, you can install vllm-ascend in three ways as follows. You can choose the one that suits your needs.
+
+### Install from PyPI
+
+>Note: Make sure Python is installed. It's recommended to use Python 3.10.
+
+There are two ways to install vllm-ascend based on the version of vllm. You can choose the one that suits your needs.
+
+#### Install version 0.7.1
+
+1. Since vllm 0.7.1 doesn't work with pip on CPU, you need build vllm from source code
+
+    ```bash
+    git clone --depth 1 --branch v0.7.1 https://github.com/vllm-project/vllm
+    cd vllm
+    python setup.py install
+    ```
+
+2. Install torch cpu version
+
+    ```bash
+    pip install torch==2.5.1  -f https://download.pytorch.org/whl/torch/
+    ```
+
+3. Install torch_npu
+
+    ```bash
+    TODO: Update the link to the right version, once it's available.
+    pip install xxx
+    ```
+
+4. Install vllm-ascend
+
+    ```bash
+    pip install vllm-ascend==0.7.1
+    ```
+
+#### Install version >= 0.7.3 (Not supported yet)
+
+1. Install torch cpu version
+
+    ```bash
+    pip install torch==2.5.1  -f https://download.pytorch.org/whl/torch/
+    ```
+
+2. Install vllm-ascend
+
+    ```bash
+    # It'll install vllm and torch_npu automatically.
+    pip install vllm-ascend
+    ```
+
+### Install from Docker image
+
+We have provided vllm-ascend official docker image for you to use. You can use the following command to pull and run the image easily.
 
 ```bash
+docker pull ascendai/vllm-ascend:latest
+
 docker run \
     --name vllm-ascend-env \
     --device /dev/davinci1 \
@@ -28,28 +82,21 @@ docker run \
     -v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
     -v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
     -v /etc/ascend_install.info:/etc/ascend_install.info \
-    -it quay.io/ascend/cann:8.0.rc3.beta1-910b-ubuntu22.04-py3.10 bash
+    -it quay.io/ascend/vllm-ascend:0.7.1 bash
 ```
 
-You do not need to install `torch` and `torch_npu` manually, they will be automatically installed as `vllm-ascend` dependencies.
-
-#### Manual installation
+Then you will enter the container which has installed vllm-ascend 0.7.1 already.
 
-Or follow the instructions provided in the [Ascend Installation Guide](https://ascend.github.io/docs/sources/ascend/quick_install.html) to set up the environment.
+### Install from source code
 
-### 3. Building
-
-#### Build Python package from source
+If you want to install vllm-ascend from source code to test the newest code with main branch of vllm, or you want to contribute to vllm-ascend, you can use the following command to install it.
 
 ```bash
-git clone https://github.com/vllm-project/vllm-ascend.git
-cd vllm-ascend
-pip install -e .
-```
+git clone https://github.com/vllm-project/vllm
+cd vllm
+python setup.py install
 
-#### Build container image from source
-```bash
 git clone https://github.com/vllm-project/vllm-ascend.git
 cd vllm-ascend
-docker build -t vllm-ascend-dev-image -f ./Dockerfile .
+pip install -e .
 ```