docs: update docs (#533)

docs/source/conf.py

@@ -15,8 +15,9 @@ author = "Nunchaku Team"
 version_path = Path(__file__).parent.parent.parent / "nunchaku" / "__version__.py"
 version_ns = {}
 exec(version_path.read_text(), {}, version_ns)
-version = release = version_ns["__version__"]
-# release = version
+version = version_ns["__version__"]
+version = version.replace("dev", "")
+release = version
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration

docs/source/index.rst

 Nunchaku Documentation
 ======================
 **Nunchaku** is a high-performance inference engine optimized for low-bit diffusion models and LLMs,
-as introduced in our paper `SVDQuant <svdquant_paper>`_.
-Check out `DeepCompressor <deepcompressor_repo>`_ for the quantization library.
+as introduced in our paper `SVDQuant <svdquant_paper_>`_.
+Check out `DeepCompressor <deepcompressor_repo_>`_ for the quantization library.
 
 .. toctree::
    :maxdepth: 2
@@ -36,8 +36,8 @@ Check out `DeepCompressor <deepcompressor_repo>`_ for the quantization library.
     :caption: Useful Tools
     :titlesonly:
 
-    ComfyUI Support: ComfyUI-nunchaku Plugin <https://github.com/mit-han-lab/ComfyUI-nunchaku>
-    Customized Model Quantization: DeepCompressor <https://github.com/mit-han-lab/deepcompressor>
+    ComfyUI Plugin: ComfyUI-nunchaku <https://github.com/mit-han-lab/ComfyUI-nunchaku>
+    Custom Model Quantization: DeepCompressor <https://github.com/mit-han-lab/deepcompressor>
     Gradio Demos <https://github.com/mit-han-lab/nunchaku/tree/main/app>