Feature(MInference): style

app.py

@@ -14,9 +14,7 @@ HF_TOKEN = os.environ.get("HF_TOKEN", None)
 
 
 DESCRIPTION = """
-<div>
-<h1>MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention (Under Review, ES-FoMo @ ICML'24)</h1>
-</div>
+# MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention (Under Review, ES-FoMo @ ICML'24)
 
 _Huiqiang Jiang†, Yucheng Li†, Chengruidong Zhang†, Qianhui Wu, Xufang Luo, Surin Ahn, Zhenhua Han, Amir H. Abdi, Dongsheng Li, Chin-Yew Lin, Yuqing Yang and Lili Qiu_
 
@@ -24,10 +22,8 @@ _Huiqiang Jiang†, Yucheng Li†, Chengruidong Zhang†, Qianhui Wu, Xufang Luo
 <a href="https://aka.ms/MInference" target="blank"> [Project Page]</a>
 <a href="https://arxiv.org/abs/2407" target="blank"> [Paper]</a></h3>
 
-<h2>News</h2>
-<ol>
-    <li><p><b>🧩</b> &#160;We will present <font color="#337ab7"><b>MInference 1.0</b></font> at the <font color="#337ab7"><b>Microsoft Booth</b></font> and <font color="#337ab7"><b>ES-FoMo</b></font> at <b>ICML'24</b>. See you in Vienna!.
-</ol>
+## News
+- 🧩 We will present **MInference 1.0** at the _**Microsoft Booth**_ and _**ES-FoMo**_ at ICML'24. See you in Vienna!
 
 <font color="brown"><b>This is only a deployment demo. Due to limited GPU resources, we do not provide an online demo. You will need to follow the code below to try MInference locally.</b></font>
 
@@ -38,7 +34,6 @@ pip install -r requirments.txt
 pip install flash_attn pycuda==2023.1
 python app.py
 ```
-<br/>
 """
 
 LICENSE = """