[Doc] Update user doc index (#1581)

Add user doc index to make the user guide more clear
- vLLM version: v0.9.1
- vLLM main:
vllm-project/vllm@49e8c7e

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

Author: wangxiyuan

docs/source/index.md

@@ -43,16 +43,10 @@ faqs
 :::{toctree}
 :caption: User Guide
 :maxdepth: 1
-user_guide/suppoted_features
-user_guide/supported_models
-user_guide/env_vars
-user_guide/additional_config
-user_guide/sleep_mode
-user_guide/graph_mode.md
-user_guide/lora.md
-user_guide/quantization.md
+user_guide/support_matrix/index
+user_guide/configuration/index
+user_guide/feature_guide/index
 user_guide/release_notes
-user_guide/structured_output
 :::
 
 % How to contribute to the vLLM Ascend project

docs/source/tutorials/multi_node.md

@@ -54,7 +54,7 @@ hccn_tool -i 0 -ping -g address 10.20.0.20
 ```
 
 ## Run with docker
-Assume you have two Altas 800 A2(64G*8) nodes, and want to deploy the `deepseek-v3-w8a8` quantitative model across multi-node.
+Assume you have two Atlas 800 A2(64G*8) nodes, and want to deploy the `deepseek-v3-w8a8` quantitative model across multi-node.
 
 ```shell
 # Define the image and container name

docs/source/user_guide/additional_config.md renamed to docs/source/user_guide/configuration/additional_config.md

@@ -2,7 +2,7 @@
 
 vllm-ascend uses the following environment variables to configure the system:
 
-:::{literalinclude} ../../../vllm_ascend/envs.py
+:::{literalinclude} ../../../../vllm_ascend/envs.py
 :language: python
 :start-after: begin-env-vars-definition
 :end-before: end-env-vars-definition

docs/source/user_guide/env_vars.md renamed to docs/source/user_guide/configuration/env_vars.md

@@ -0,0 +1,10 @@
+# Configuration Guide
+
+This section provides a detailed configuration guide of vLLM Ascend.
+
+:::{toctree}
+:caption: Configuration Guide
+:maxdepth: 1
+env_vars
+additional_config
+:::

docs/source/user_guide/configuration/index.md

@@ -59,7 +59,7 @@ online example:
 vllm serve Qwen/Qwen2-7B-Instruct --additional-config='{"torchair_graph_config": {"enabled": true},"ascend_scheduler_config": {"enabled": true,}}'
 ```
 
-You can find more detail about additional config [here](./additional_config.md)
+You can find more detail about additional config [here](../configuration/additional_config.md).
 
 ## Fallback to Eager Mode
 

docs/source/user_guide/graph_mode.md renamed to docs/source/user_guide/feature_guide/graph_mode.md

@@ -0,0 +1,13 @@
+# Feature Guide
+
+This section provides a detailed usage guide of vLLM Ascend features.
+
+:::{toctree}
+:caption: Feature Guide
+:maxdepth: 1
+graph_mode
+quantization
+sleep_mode
+structured_output
+lora
+:::

docs/source/user_guide/images/structured_output_1.png renamed to docs/source/user_guide/feature_guide/images/structured_output_1.png

@@ -1,4 +1,4 @@
-# LoRA Adapters
+# LoRA Adapters Guide
 
 Like vLLM, vllm-ascend supports LoRA as well. The usage and more details can be found in [vLLM official document](https://docs.vllm.ai/en/latest/features/lora.html).