update docs (#62)

Author: HuiResearch

README.MD

@@ -1,7 +1,7 @@
 <div align="center">
   <img src="docs/zh/_img/icon.png" width="450" alt="FlashTTS Logo"/>
 
-[📘 Documentation](docs/zh/README.MD)
+[📘 Documentation](docs/zh/README.MD) | [📚 Deepwiki](https://deepwiki.com/HuiResearch/FlashTTS)
 
 [中文](README.MD) | [English](README_EN.MD)
 
@@ -212,6 +212,7 @@ flashtts infer \
  --host 0.0.0.0 \
  --port 8000
  ```
+详细部署说明，请参考：[server.md](docs/zh/server/server.md)
 
 ## ⚡ 推理速度
 

README_EN.MD

@@ -1,7 +1,7 @@
 <div align="center">
   <img src="docs/zh/_img/icon.png" width="450" alt="FlashTTS Logo"/>
 
-[📘 Documentation](docs/en/README.MD)
+[📘 Documentation](docs/zh/README.MD) | [📚 Deepwiki](https://deepwiki.com/HuiResearch/FlashTTS)
 
 [中文](README.MD) | [English](README_EN.MD)
 
@@ -164,6 +164,8 @@ Server deployment:
  --port 8000
  ```
 
+For detailed deployment，please refer to: [server.md](docs/en/server/server.md)
+
 ## ⚡ Inference Speed
 
 Test environment: `A800 GPU` · Model: `Spark-TTS-0.5B` · Test script: [speed_test.py](examples/speed_test.py)

docs/en/server/server.md

@@ -5,6 +5,7 @@
 1. Refer to the installation guide: [installation.md](../get_started/installation.md)
 2. Start the server:
 
+   - spark tts
    ```bash
    flashtts serve \
    --model_path Spark-TTS-0.5B \ # Change to your model path if needed
@@ -20,6 +21,35 @@
    --host 0.0.0.0 \
    --port 8000
    ```
+   - mega tts
+   ```bash
+    flashtts serve \
+    --model_path MegaTTS3 \ # Change to your model path if needed
+    --backend vllm \ # vllm、sglang、torch、llama-cpp、mlx-lm任选一个
+    --llm_device cuda \
+    --tokenizer_device cuda \
+    --llm_attn_implementation sdpa \ # Recommended for torch backend
+    --torch_dtype "float16" \ 
+    --max_length 8192 \
+    --llm_gpu_memory_utilization 0.6 \
+    --host 0.0.0.0 \
+    --port 8000
+    ```
+   - orphpeus tts
+   ```bash
+    flashtts serve \
+    --model_path orpheus-3b-0.1-ft-bf16 \ # Change to your model path if needed
+    --lang english \
+    --backend vllm \ # vllm、sglang、torch、llama-cpp、mlx-lm任选一个
+    --llm_device cuda \
+    --detokenizer_device cuda \
+    --llm_attn_implementation sdpa \ # Recommended for torch backend
+    --torch_dtype "float16" \ 
+    --max_length 8192 \
+    --llm_gpu_memory_utilization 0.6 \
+    --host 0.0.0.0 \
+    --port 8000
+    ```
 
 3. Access the web interface:
    ```

docs/zh/server/server.md

@@ -4,23 +4,53 @@
 
 1. 参考安装文档: [installation.md](../get_started/installation.md)
 2. 启动服务：
+   
+   - spark tts
    ```bash
-
     flashtts serve \
     --model_path Spark-TTS-0.5B \ # 可修改为自己的模型地址
     --backend vllm \ # vllm、sglang、torch、llama-cpp、mlx-lm任选一个
     --llm_device cuda \
     --tokenizer_device cuda \
     --detokenizer_device cuda \
     --wav2vec_attn_implementation sdpa \
-    --llm_attn_implementation sdpa \ # 如果使用torch engine，最好开启加速
+    --llm_attn_implementation sdpa \ # 如果backend为torch，最好开启加速
     --torch_dtype "bfloat16" \ # 对于spark-tts模型，不支持bfloat16的设备，只能设置为float32.
     --max_length 32768 \
     --llm_gpu_memory_utilization 0.6 \
     --host 0.0.0.0 \
     --port 8000
-    
     ```
+   - mega tts
+   ```bash
+    flashtts serve \
+    --model_path MegaTTS3 \ # 可修改为自己的模型地址
+    --backend vllm \ # vllm、sglang、torch、llama-cpp、mlx-lm任选一个
+    --llm_device cuda \
+    --tokenizer_device cuda \
+    --llm_attn_implementation sdpa \ # 如果backend为torch，最好开启加速
+    --torch_dtype "float16" \ 
+    --max_length 8192 \
+    --llm_gpu_memory_utilization 0.6 \
+    --host 0.0.0.0 \
+    --port 8000
+    ```
+   - orphpeus tts
+   ```bash
+    flashtts serve \
+    --model_path orpheus-3b-0.1-ft-bf16 \ # 可修改为自己的模型地址
+    --lang english \
+    --backend vllm \ # vllm、sglang、torch、llama-cpp、mlx-lm任选一个
+    --llm_device cuda \
+    --detokenizer_device cuda \
+    --llm_attn_implementation sdpa \ # 如果backend为torch，最好开启加速
+    --torch_dtype "float16" \ 
+    --max_length 8192 \
+    --llm_gpu_memory_utilization 0.6 \
+    --host 0.0.0.0 \
+    --port 8000
+    ```
+   
 3. 在浏览器中访问页面
 
   ```