update lserve

ys-2020 · Feb 24, 2025 · b463284 · b463284
1 parent e6c7f8b
commit b463284
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 1 deletion.
diff --git a/_data/publications.yml b/_data/publications.yml
@@ -1,11 +1,19 @@
 main:
 
+  - title: "LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention"
+    authors: <strong>Shang Yang*</strong>, Junxian Guo*, Haotian Tang, Qinghao Hu, Guangxuan Xiao, Jiaming Tang, Yujun Lin, Zhijian Liu, Yao Lu, Song Han.
+    conference_short: MLSys
+    conference: The Eighth Annual Conference on Machine Learning and Systems <strong>(MLSys)</strong>, 2025. 
+    paper: https://arxiv.org/abs/2502.14866
+    code: https://github.com/mit-han-lab/omniserve
+    image: ./assets/img/paper_teasers/LServe.png
+
   - title: "QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving"
     authors: Yujun Lin*, Haotian Tang*, <strong>Shang Yang*</strong>, Zhekai Zhang, Guangxuan Xiao, Chuang Gan, Song Han.
     conference_short: MLSys
     conference: The Eighth Annual Conference on Machine Learning and Systems <strong>(MLSys)</strong>, 2025. 
     paper: https://arxiv.org/abs/2405.04532
-    code: https://github.com/mit-han-lab/qserve
+    code: https://github.com/mit-han-lab/omniserve
     image: ./assets/img/paper_teasers/QServe.png
 
   - title: "AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration"

diff --git a/assets/img/paper_teasers/LServe.png b/assets/img/paper_teasers/LServe.png