Update documentation from main repository

Author: future-xy

docs/README.md

@@ -1,6 +1,6 @@
 # ServerlessLLM documents
 
-Please find our documents in [ServerlessLLM](https://serverlessllm.github.io/docs/getting_started).
+Please find our documents in [ServerlessLLM](https://serverlessllm.github.io/docs/intro).
 
 ## How to build ServerlessLLM Docs
 

docs/api/sllm-store-cli.md

@@ -208,7 +208,7 @@ sllm-store load [OPTIONS]
   - Adapter name to save. Must be a Hugging Face pretrained LoRA adapter name.
 
 - `--precision <precision>`
-  - Precision to use when loading the model (`transformers` backend only). For more info on quantization in ServerlessLLM, visit [here](https://serverlessllm.github.io/docs/store/quickstart#quantization).
+  - Precision to use when loading the model (`transformers` backend only). For more info on quantization in ServerlessLLM, visit [here](../store/quantization.md).
 
 - `--storage-path <storage_path>`
   - Location where the model will be loaded from.

docs/developer/supporting_a_new_hardware.md

@@ -18,7 +18,7 @@ Hardware is considered supported by ServerlessLLM if:
    - For non-CUDA-compatible APIs, implementing a custom checkpoint loading function might be required.
 
 ## Verifying Hardware Support in ServerlessLLM Store
-The hardware support is verified if it successfully completes the [Quick Start Guide](https://serverlessllm.github.io/docs/getting_started/) examples, showcasing checkpoint loading and inference functionality without errors.
+The hardware support is verified if it successfully completes the [Quick Start Guide](../getting_started.md) examples, showcasing checkpoint loading and inference functionality without errors.
 
 If the hardware is not publicly available (i.e., can't be tested by the ServerlessLLM team), a screenshot or output log of the successful execution of the Quick Start Guide examples is required to verify hardware support.
 

docs/store/rocm_quickstart.md

@@ -135,7 +135,7 @@ Prompt: 'Hello, my name is', Generated text: ' Joel, my dad is my friend and we
 Prompt: 'The president of the United States is', Generated text: ' speaking out against the release of some State Department documents which show the Russians were involved'
 Prompt: 'The capital of France is', Generated text: ' a worldwide knowledge center. What better place to learn about the history and culture of'
 Prompt: 'The future of AI is', Generated text: " here: it's the future of everything\nIf you want to test your minds"
-[rank0]:[W605 13:03:30.532018298 ProcessGroupNCCL.cpp:1476] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/distributed.html#shutdown (function operator())
+[rank0]:[W605 13:03:30.532018298 ProcessGroupNCCL.cpp:1476] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/stable/distributed.html#shutdown (function operator())
 ```
 
 ## Build the wheel from source and install