Spaces:
Runtime error
Runtime error
Feature(MInference): update information
Browse files
app.py
CHANGED
|
@@ -14,8 +14,9 @@ HF_TOKEN = os.environ.get("HF_TOKEN", None)
|
|
| 14 |
|
| 15 |
|
| 16 |
DESCRIPTION = """
|
| 17 |
-
|
| 18 |
-
# MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention (Under Review, ES-FoMo @ ICML'24)
|
|
|
|
| 19 |
_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_
|
| 20 |
|
| 21 |
<h3 style="text-align: center;"><a href="https://github.com/microsoft/MInference" target="blank"> [Code]</a>
|
|
|
|
| 14 |
|
| 15 |
|
| 16 |
DESCRIPTION = """
|
| 17 |
+
|
| 18 |
+
# MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention (Under Review, ES-FoMo @ ICML'24)
|
| 19 |
+
|
| 20 |
_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_
|
| 21 |
|
| 22 |
<h3 style="text-align: center;"><a href="https://github.com/microsoft/MInference" target="blank"> [Code]</a>
|