diff --git a/README.md b/README.md
index 1b8fe3aa..f09f1627 100644
--- a/README.md
+++ b/README.md
@@ -1,5 +1,5 @@
 > [!IMPORTANT]
-> ***`bigdl-llm` has now become `ipex-llm` (see the migration guide [here](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/bigdl_llm_migration.html)); you may find the original `BigDL` project [here](https://github.com/intel-analytics/BigDL-2.x).***
+> ***`bigdl-llm` has now become `ipex-llm` (see the migration guide [here](docs/mddocs/Quickstart/bigdl_llm_migration.md)); you may find the original `BigDL` project [here](https://github.com/intel-analytics/BigDL-2.x).***
  
 ---
 
@@ -7,7 +7,7 @@
 **`IPEX-LLM`** is a PyTorch library for running **LLM** on Intel CPU and GPU *(e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max)* with very low latency[^1]. 
 > [!NOTE]
 > - *It is built on top of the excellent work of **`llama.cpp`**, **`transformers`**, **`bitsandbytes`**, **`vLLM`**, **`qlora`**, **`AutoGPTQ`**, **`AutoAWQ`**, etc.*
-> - *It provides seamless integration with [llama.cpp](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/llama_cpp_quickstart.html), [Ollama](https://ipex-llm.readthedocs.io/en/main/doc/LLM/Quickstart/ollama_quickstart.html), [Text-Generation-WebUI](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/webui_quickstart.html), [HuggingFace transformers](python/llm/example/GPU/HF-Transformers-AutoModels), [LangChain](python/llm/example/GPU/LangChain), [LlamaIndex](python/llm/example/GPU/LlamaIndex), [DeepSpeed-AutoTP](python/llm/example/GPU/Deepspeed-AutoTP), [vLLM](python/llm/example/GPU/vLLM-Serving), [FastChat](python/llm/src/ipex_llm/serving/fastchat), [Axolotl](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/axolotl_quickstart.html), [HuggingFace PEFT](python/llm/example/GPU/LLM-Finetuning), [HuggingFace TRL](python/llm/example/GPU/LLM-Finetuning/DPO), [AutoGen](python/llm/example/CPU/Applications/autogen), [ModeScope](python/llm/example/GPU/ModelScope-Models), etc.* 
+> - *It provides seamless integration with [llama.cpp](docs/mddocs/Quickstart/llama_cpp_quickstart.md), [Ollama](docs/mddocs/Quickstart/ollama_quickstart.md), [Text-Generation-WebUI](docs/mddocs/Quickstart/webui_quickstart.md), [HuggingFace transformers](python/llm/example/GPU/HF-Transformers-AutoModels), [LangChain](python/llm/example/GPU/LangChain), [LlamaIndex](python/llm/example/GPU/LlamaIndex), [DeepSpeed-AutoTP](python/llm/example/GPU/Deepspeed-AutoTP), [vLLM](docs/mddocs/Quickstart/vLLM_quickstart.md), [FastChat](docs/mddocs/Quickstart/fastchat_quickstart.md), [Axolotl](docs/mddocs/Quickstart/axolotl_quickstart.md), [HuggingFace PEFT](python/llm/example/GPU/LLM-Finetuning), [HuggingFace TRL](python/llm/example/GPU/LLM-Finetuning/DPO), [AutoGen](python/llm/example/CPU/Applications/autogen), [ModeScope](python/llm/example/GPU/ModelScope-Models), etc.* 
 > - ***50+ models** have been optimized/verified on `ipex-llm` (including LLaMA2, Mistral, Mixtral, Gemma, LLaVA, Whisper, ChatGLM, Baichuan, Qwen, RWKV, and more); see the complete list [here](#verified-models).*
 
 ## `ipex-llm` Performance
@@ -28,7 +28,7 @@ See the **Token Generation Speed** on *Intel Core Ultra* and *Intel Arc GPU* bel
   </tr>
 </table>
 
-You may follow the [guide](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/benchmark_quickstart.html) to run `ipex-llm` performance benchmark yourself.
+You may follow the [Benchmarking Guide](docs/mddocs/Quickstart/benchmark_quickstart.md) to run `ipex-llm` performance benchmark yourself.
 
 ## `ipex-llm` Demo
 
@@ -65,16 +65,16 @@ See demos of running local LLMs *on Intel Iris iGPU, Intel Core Ultra iGPU, sing
   </tr>
   <tr>
     <td align="center" width="25%">
-      <a href="https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/llama_cpp_quickstart.html">llama.cpp (Phi-3-mini Q4_0)</a>
+      <a href="docs/mddocs/Quickstart/llama_cpp_quickstart.md">llama.cpp (Phi-3-mini Q4_0)</a>
     </td>
     <td align="center" width="25%">
-      <a href="https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/ollama_quickstart.html">Ollama (Mistral-7B Q4_K) </a>
+      <a href="docs/mddocs/Quickstart/ollama_quickstart.md">Ollama (Mistral-7B Q4_K) </a>
     </td>
     <td align="center" width="25%">
-      <a href="https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/webui_quickstart.html">TextGeneration-WebUI (Llama3-8B FP8) </a>
+      <a href="docs/mddocs/Quickstart/webui_quickstart.md">TextGeneration-WebUI (Llama3-8B FP8) </a>
     </td>
     <td align="center" width="25%">
-      <a href="https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/fastchat_quickstart.html">FastChat (QWen1.5-32B FP6)</a>
+      <a href="docs/mddocs/Quickstart/fastchat_quickstart.md">FastChat (QWen1.5-32B FP6)</a>
     </td>  </tr>
 </table>
 
@@ -126,17 +126,17 @@ Please see the **Perplexity** result below (tested on Wikitext dataset using the
 
 ## Latest Update 🔥 
 - [2024/05] You can now easily run `ipex-llm` inference, serving and finetuning using [Docker](#docker).
-- [2024/05] You can now install `ipex-llm` on Windows using just "*[one command](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/install_windows_gpu.html#install-ipex-llm)*".
-- [2024/05] `ipex-llm` now supports **Axolotl** for LLM finetuning on Intel GPU; see the quickstart [here](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/axolotl_quickstart.html).
-- [2024/04] You can now run **Open WebUI** on Intel GPU using `ipex-llm`; see the quickstart [here](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/open_webui_with_ollama_quickstart.html).
-- [2024/04] You can now run **Llama 3** on Intel GPU using `llama.cpp` and `ollama` with `ipex-llm`; see the quickstart [here](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/llama3_llamacpp_ollama_quickstart.html).
+- [2024/05] You can now install `ipex-llm` on Windows using just "*[one command](docs/mddocs/Quickstart/install_windows_gpu.md#install-ipex-llm)*".
+- [2024/05] `ipex-llm` now supports **Axolotl** for LLM finetuning on Intel GPU; see the quickstart [here](docs/mddocs/Quickstart/axolotl_quickstart.md).
+- [2024/04] You can now run **Open WebUI** on Intel GPU using `ipex-llm`; see the quickstart [here](docs/mddocs/Quickstart/open_webui_with_ollama_quickstart.md).
+- [2024/04] You can now run **Llama 3** on Intel GPU using `llama.cpp` and `ollama` with `ipex-llm`; see the quickstart [here](docs/mddocs/Quickstart/llama3_llamacpp_ollama_quickstart.md).
 - [2024/04] `ipex-llm` now supports **Llama 3** on both Intel [GPU](python/llm/example/GPU/HF-Transformers-AutoModels/Model/llama3) and [CPU](python/llm/example/CPU/HF-Transformers-AutoModels/Model/llama3).
-- [2024/04] `ipex-llm` now provides C++ interface, which can be used as an accelerated backend for running [llama.cpp](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/llama_cpp_quickstart.html) and [ollama](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/ollama_quickstart.html) on Intel GPU.
-- [2024/03] `bigdl-llm` has now become `ipex-llm` (see the migration guide [here](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/bigdl_llm_migration.html)); you may find the original `BigDL` project [here](https://github.com/intel-analytics/bigdl-2.x).
+- [2024/04] `ipex-llm` now provides C++ interface, which can be used as an accelerated backend for running [llama.cpp](docs/mddocs/Quickstart/llama_cpp_quickstart.md) and [ollama](docs/mddocs/Quickstart/ollama_quickstart.md) on Intel GPU.
+- [2024/03] `bigdl-llm` has now become `ipex-llm` (see the migration guide [here](docs/mddocs/Quickstart/bigdl_llm_migration.md)); you may find the original `BigDL` project [here](https://github.com/intel-analytics/bigdl-2.x).
 - [2024/02] `ipex-llm` now supports directly loading model from [ModelScope](python/llm/example/GPU/ModelScope-Models) ([魔搭](python/llm/example/CPU/ModelScope-Models)).
 - [2024/02] `ipex-llm` added initial **INT2** support (based on llama.cpp [IQ2](python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/GGUF-IQ2) mechanism), which makes it possible to run large-size LLM (e.g., Mixtral-8x7B) on Intel GPU with 16GB VRAM.
 - [2024/02] Users can now use `ipex-llm` through [Text-Generation-WebUI](https://github.com/intel-analytics/text-generation-webui) GUI.
-- [2024/02] `ipex-llm` now supports *[Self-Speculative Decoding](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Inference/Self_Speculative_Decoding.html)*, which in practice brings **~30% speedup** for FP16 and BF16 inference latency on Intel [GPU](python/llm/example/GPU/Speculative-Decoding) and [CPU](python/llm/example/CPU/Speculative-Decoding) respectively.
+- [2024/02] `ipex-llm` now supports *[Self-Speculative Decoding](docs/mddocs/Inference/Self_Speculative_Decoding.md)*, which in practice brings **~30% speedup** for FP16 and BF16 inference latency on Intel [GPU](python/llm/example/GPU/Speculative-Decoding) and [CPU](python/llm/example/CPU/Speculative-Decoding) respectively.
 - [2024/02] `ipex-llm` now supports a comprehensive list of LLM **finetuning** on Intel GPU (including [LoRA](python/llm/example/GPU/LLM-Finetuning/LoRA), [QLoRA](python/llm/example/GPU/LLM-Finetuning/QLoRA), [DPO](python/llm/example/GPU/LLM-Finetuning/DPO), [QA-LoRA](python/llm/example/GPU/LLM-Finetuning/QA-LoRA) and [ReLoRA](python/llm/example/GPU/LLM-Finetuning/ReLora)).
 - [2024/01] Using `ipex-llm` [QLoRA](python/llm/example/GPU/LLM-Finetuning/QLoRA), we managed to finetune LLaMA2-7B in **21 minutes** and LLaMA2-70B in **3.14 hours** on 8 Intel Max 1550 GPU for [Standford-Alpaca](python/llm/example/GPU/LLM-Finetuning/QLoRA/alpaca-qlora) (see the blog [here](https://www.intel.com/content/www/us/en/developer/articles/technical/finetuning-llms-on-intel-gpus-using-bigdl-llm.html)).
 <details><summary>More updates</summary>
@@ -160,32 +160,32 @@ Please see the **Perplexity** result below (tested on Wikitext dataset using the
 ## `ipex-llm` Quickstart
 
 ### Docker
-- [GPU Inference in C++](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/DockerGuides/docker_cpp_xpu_quickstart.html): running `llama.cpp`, `ollama`, `OpenWebUI`, etc., with `ipex-llm` on Intel GPU
-- [GPU Inference in Python](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/DockerGuides/docker_pytorch_inference_gpu.html) : running HuggingFace `transformers`, `LangChain`, `LlamaIndex`, `ModelScope`, etc. with `ipex-llm` on Intel GPU
-- [vLLM on GPU](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/DockerGuides/vllm_docker_quickstart.html): running `vLLM` serving with `ipex-llm` on Intel GPU 
-- [FastChat on GPU](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/DockerGuides/fastchat_docker_quickstart.html): running `FastChat` serving with `ipex-llm` on Intel GPU
+- [GPU Inference in C++](docs/mddocs/DockerGuides/docker_cpp_xpu_quickstart.md): running `llama.cpp`, `ollama`, `OpenWebUI`, etc., with `ipex-llm` on Intel GPU
+- [GPU Inference in Python](docs/mddocs/DockerGuides/docker_pytorch_inference_gpu.md) : running HuggingFace `transformers`, `LangChain`, `LlamaIndex`, `ModelScope`, etc. with `ipex-llm` on Intel GPU
+- [vLLM on GPU](docs/mddocs/DockerGuides/vllm_docker_quickstart.md): running `vLLM` serving with `ipex-llm` on Intel GPU 
+- [FastChat on GPU](docs/mddocs/DockerGuides/fastchat_docker_quickstart.md): running `FastChat` serving with `ipex-llm` on Intel GPU
 
 ### Use
-- [llama.cpp](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/llama_cpp_quickstart.html): running **llama.cpp** (*using C++ interface of `ipex-llm` as an accelerated backend for `llama.cpp`*) on Intel GPU
-- [Ollama](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/ollama_quickstart.html): running **ollama** (*using C++ interface of `ipex-llm` as an accelerated backend for `ollama`*) on Intel GPU
-- [vLLM](python/llm/example/GPU/vLLM-Serving): running `ipex-llm` in **vLLM** on both Intel [GPU](python/llm/example/GPU/vLLM-Serving) and [CPU](python/llm/example/CPU/vLLM-Serving)
-- [FastChat](python/llm/src/ipex_llm/serving/fastchat): running `ipex-llm` in **FastChat** serving on on both Intel GPU and CPU
-- [Text-Generation-WebUI](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/webui_quickstart.html): running `ipex-llm` in `oobabooga` **WebUI**
-- [Axolotl](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/axolotl_quickstart.html): running `ipex-llm` in **Axolotl** for LLM finetuning
-- [Benchmarking](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/benchmark_quickstart.html): running  (latency and throughput) **benchmarks** for `ipex-llm` on Intel CPU and GPU
+- [llama.cpp](docs/mddocs/Quickstart/llama_cpp_quickstart.md): running **llama.cpp** (*using C++ interface of `ipex-llm` as an accelerated backend for `llama.cpp`*) on Intel GPU
+- [Ollama](docs/mddocs/Quickstart/ollama_quickstart.md): running **ollama** (*using C++ interface of `ipex-llm` as an accelerated backend for `ollama`*) on Intel GPU
+- [vLLM](docs/mddocs/Quickstart/vLLM_quickstart.md): running `ipex-llm` in **vLLM** on both Intel [GPU](python/llm/example/GPU/vLLM-Serving) and [CPU](python/llm/example/CPU/vLLM-Serving)
+- [FastChat](docs/mddocs/Quickstart/fastchat_quickstart.md): running `ipex-llm` in **FastChat** serving on on both Intel GPU and CPU
+- [Text-Generation-WebUI](docs/mddocs/Quickstart/webui_quickstart.md): running `ipex-llm` in `oobabooga` **WebUI**
+- [Axolotl](docs/mddocs/Quickstart/axolotl_quickstart.md): running `ipex-llm` in **Axolotl** for LLM finetuning
+- [Benchmarking](docs/mddocs/Quickstart/benchmark_quickstart.md): running  (latency and throughput) **benchmarks** for `ipex-llm` on Intel CPU and GPU
 
 ### Applications
-- [Local RAG](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/chatchat_quickstart.html): running `LangChain-Chatchat` (*Knowledge Base QA using **RAG** pipeline*) with `ipex-llm`
-- [Coding copilot](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/continue_quickstart.html): running `Continue` (coding copilot in VSCode) with `ipex-llm`
-- [Open WebUI](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/open_webui_with_ollama_quickstart.html): running `Open WebUI` with `ipex-llm`
-- [PrivateGPT](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/privateGPT_quickstart.html): running `PrivateGPT` to interact with documents with `ipex-llm`
-- [Dify platform](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/dify_quickstart.html): running `ipex-llm` in `Dify`(*production-ready LLM app development platform*)
+- [Local RAG](docs/mddocs/Quickstart/chatchat_quickstart.md): running `LangChain-Chatchat` (*Knowledge Base QA using **RAG** pipeline*) with `ipex-llm`
+- [Coding copilot](docs/mddocs/Quickstart/continue_quickstart.md): running `Continue` (coding copilot in VSCode) with `ipex-llm`
+- [Open WebUI](docs/mddocs/Quickstart/open_webui_with_ollama_quickstart.md): running `Open WebUI` with `ipex-llm`
+- [PrivateGPT](docs/mddocs/Quickstart/privateGPT_quickstart.md): running `PrivateGPT` to interact with documents with `ipex-llm`
+- [Dify platform](docs/mddocs/Quickstart/dify_quickstart.md): running `ipex-llm` in `Dify`(*production-ready LLM app development platform*)
 
 
 ### Install 
-- [Windows GPU](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/install_windows_gpu.html): installing `ipex-llm` on Windows with Intel GPU
-- [Linux GPU](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/install_linux_gpu.html): installing `ipex-llm` on Linux with Intel GPU
-- *For more details, please refer to the [installation guide](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Overview/install.html)*
+- [Windows GPU](docs/mddocs/Quickstart/install_windows_gpu.md): installing `ipex-llm` on Windows with Intel GPU
+- [Linux GPU](docs/mddocs/Quickstart/install_linux_gpu.md): installing `ipex-llm` on Linux with Intel GPU
+- *For more details, please refer to the [full installation guide](docs/mddocs/Overview/install.md)*
 
 
 ### Code Examples
@@ -195,8 +195,8 @@ Please see the **Perplexity** result below (tested on Wikitext dataset using the
   - [INT8 inference](python/llm/example/GPU/HF-Transformers-AutoModels/More-Data-Types): **INT8** LLM inference on Intel [GPU](python/llm/example/GPU/HF-Transformers-AutoModels/More-Data-Types) and [CPU](python/llm/example/CPU/HF-Transformers-AutoModels/More-Data-Types)
   - [INT2 inference](python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/GGUF-IQ2): **INT2** LLM inference (based on llama.cpp IQ2 mechanism) on Intel [GPU](python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/GGUF-IQ2)
 - FP16/BF16 inference
-  - **FP16** LLM inference on Intel [GPU](python/llm/example/GPU/Speculative-Decoding), with possible [self-speculative decoding](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Inference/Self_Speculative_Decoding.html) optimization
-  - **BF16** LLM inference on Intel [CPU](python/llm/example/CPU/Speculative-Decoding), with possible [self-speculative decoding](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Inference/Self_Speculative_Decoding.html) optimization 
+  - **FP16** LLM inference on Intel [GPU](python/llm/example/GPU/Speculative-Decoding), with possible [self-speculative decoding](docs/mddocs/Inference/Self_Speculative_Decoding.md) optimization
+  - **BF16** LLM inference on Intel [CPU](python/llm/example/CPU/Speculative-Decoding), with possible [self-speculative decoding](docs/mddocs/Inference/Self_Speculative_Decoding.md) optimization 
 - Save and load
   - [Low-bit models](python/llm/example/CPU/HF-Transformers-AutoModels/Save-Load): saving and loading `ipex-llm` low-bit models
   - [GGUF](python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/GGUF): directly loading GGUF models into `ipex-llm`
@@ -211,14 +211,14 @@ Please see the **Perplexity** result below (tested on Wikitext dataset using the
   - [LangChain](python/llm/example/GPU/LangChain)
   - [LlamaIndex](python/llm/example/GPU/LlamaIndex)
   - [DeepSpeed-AutoTP](python/llm/example/GPU/Deepspeed-AutoTP)
-  - [Axolotl](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/axolotl_quickstart.html)
+  - [Axolotl](docs/mddocs/Quickstart/axolotl_quickstart.md)
   - [HuggingFace PEFT](python/llm/example/GPU/LLM-Finetuning/HF-PEFT)
   - [HuggingFace TRL](python/llm/example/GPU/LLM-Finetuning/DPO)
   - [AutoGen](python/llm/example/CPU/Applications/autogen)
   - [ModeScope](python/llm/example/GPU/ModelScope-Models)
 - [Tutorials](https://github.com/intel-analytics/ipex-llm-tutorial)
 
-*For more details, please refer to the `ipex-llm` document [website](https://ipex-llm.readthedocs.io/).*
+
 
 ## Verified Models
 Over 50 models have been optimized/verified on `ipex-llm`, including *LLaMA/LLaMA2, Mistral, Mixtral, Gemma, LLaVA, Whisper, ChatGLM2/ChatGLM3, Baichuan/Baichuan2, Qwen/Qwen-1.5, InternLM* and more; see the list below.