Merge pull request #7 from hao-ai-lab/master

update publications

content/home.md

@@ -24,7 +24,7 @@ We also develop and maintain open-source models and systems to democratize the a
 <!-- 🎉 -->
 
 {{< newsEntry >}}
-🎉🎉 In 2024, We have 1 ICLR, 1 OSDI, 6 ICML, 1 ACL, 1 COLM papers. Kudos to our lab members for a productive year!
+🎉🎉 In 2024, We have 1 ICLR, 1 OSDI, 6 ICML, 1 ACL, 1 COLM papers, 1 EMNLP, and 2 NeurIPS papers. Kudos to our lab members for a productive year!
 {{< /newsEntry >}}
 
 {{< newsEntry >}}

content/people.md

@@ -37,7 +37,10 @@ summary: people
 
 {{< lab_member name="Haoyang Yu" role="Undergrad" image="haoyang_yu.jpeg" academic="https://www.linkedin.com/in/haoyang-yu-8b1997257/">}}
 
+{{< lab_member name="Longfei Yun" role="Master's" image="longfei_yun.jpg" twitter="https://twitter.com/longfei_yu78793">}}
+
 {{< lab_member name="Siqi Zhu" role="Undergrad Intern" image="siqi_zhu.jpg" academic="https://github.com/zhusq20" twitter="https://x.com/Oliver65097212">}}
+
 {{< /lab_members_grid >}}
 
 ### Alumni

content/publications.md

@@ -7,19 +7,27 @@ summary: publications
 
 ### 2024
 
+{{< publication title="Efficient LLM Scheduling by Learning to Rank" venue="NeurIPS 2024" paperLink="https://arxiv.org/pdf/2408.15792" codeLink="https://github.com/hao-ai-lab/vllm-ltr" award="" project="" data-topic="Selected, Large Language Models, Scalable ML" >}}
+Yichao Fu, Siqi Zhu, Runlong Su, Aurick Qiao, Ion Stoica, Hao Zhang
+{{< /publication >}}
+
+{{< publication title="MPC-Minimized Secure LLM Inference" venue="Preprint 2024" paperLink="https://arxiv.org/pdf/2408.03561" codeLink="" award="" project="" data-topic="Large Language Models, ML Security" >}}
+Deevashwer Rathee*, Dacheng Li*, Ion Stoica, Hao Zhang, Raluca Ada Popa
+{{< /publication >}}
+
 {{< publication title="Optimizing Speculative Decoding for Serving Large Language Models Using Goodput" venue="Preprint 2024" paperLink="https://arxiv.org/pdf/2406.14066" codeLink="" award="" project="" data-topic="Selected, Large Language Models, Scalable ML, ML Systems" >}}
 Xiaoxuan Liu, Cade Daniel, Lanxiang Hu, Woosuk Kwon, Zhuohan Li, Xiangxi Mo, Alvin Cheung, Zhijie Deng, Ion Stoica, Hao Zhang
 {{< /publication >}}
 
-{{< publication title="AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models" venue="Preprint 2024" paperLink="https://arxiv.org/pdf/2406.13233" codeLink="" award="" project="" data-topic="Selected, Large Language Models, Scalable ML" >}}
+{{< publication title="AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models" venue="EMNLP 2024" paperLink="https://arxiv.org/pdf/2406.13233" codeLink="" award="" project="" data-topic="Selected, Large Language Models, Scalable ML" >}}
 Zihao Zeng, Yibo Miao, Hongcheng Gao, Hao Zhang, Zhijie Deng
 {{< /publication >}}
 
 {{< publication title="Toward Inference-optimal Mixture-of-Expert Large Language Models" venue="Preprint 2024" paperLink="https://arxiv.org/pdf/2404.02852" codeLink="" award="" project="" data-topic="Selected, Large Language Models" >}}
 Longfei Yun*, Yonghao Zhuang*, Yao Fu, Eric P Xing, Hao Zhang
 {{< /publication >}}
 
-{{< publication title="Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length" venue="Preprint 2024" paperLink="https://arxiv.org/pdf/2404.08801" codeLink="https://github.com/XuezheMax/megalodon" award="" project="" data-topic="Selected, Large Language Models" >}}
+{{< publication title="Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length" venue="NeurIPS 2024" paperLink="https://arxiv.org/pdf/2404.08801" codeLink="https://github.com/XuezheMax/megalodon" award="" project="" data-topic="Selected, Large Language Models" >}}
 Xuezhe Ma*, Xiaomeng Yang*, Wenhan Xiong, Beidi Chen, Lili Yu, Hao Zhang, Jonathan May, Luke Zettlemoyer, Omer Levy, Chunting Zhou*
 {{< /publication >}}
 

gen_publications.py

@@ -9,12 +9,15 @@ def convert_json_to_hugo(publications):
         year = publication["date"].split("/")[1]
         if publication["venue"]:
             venue_year = publication["venue"].split(" ")[-1]
-            if int(venue_year) > 2010:
-                year = venue_year
+            try:
+                if int(venue_year) > 2010:
+                    year = venue_year
+            except ValueError as e:
+                print(f"The publication {publication} has year {venue_year} wrong")
+                raise e
         publications_by_year[year].append(publication)
     # Sort years in descending order
     sorted_years = sorted(publications_by_year.keys(), reverse=True)
-    print(sorted_years)
     # Format publications for Hugo
     hugo_output = ""
     for year in sorted_years:

publications.json

@@ -1,4 +1,28 @@
 [
+    {
+        "title": "Efficient LLM Scheduling by Learning to Rank",
+        "authors": "Yichao Fu, Siqi Zhu, Runlong Su, Aurick Qiao, Ion Stoica, Hao Zhang",
+        "venue": "NeurIPS 2024",
+        "pdf": "https://arxiv.org/pdf/2408.15792",
+        "code": "https://github.com/hao-ai-lab/vllm-ltr",
+        "presentation": "",
+        "award": "",
+        "project": "",
+        "tag": "Selected, Large Language Models, Scalable ML",
+        "date": "08/2024"
+    },
+    {
+        "title": "MPC-Minimized Secure LLM Inference",
+        "authors": "Deevashwer Rathee*, Dacheng Li*, Ion Stoica, Hao Zhang, Raluca Ada Popa",
+        "venue": "Preprint 2024",
+        "pdf": "https://arxiv.org/pdf/2408.03561",
+        "code": "",
+        "presentation": "",
+        "award": "",
+        "project": "",
+        "tag": "Large Language Models, ML Security",
+        "date": "08/2024"
+    },
     {
         "title": "Optimizing Speculative Decoding for Serving Large Language Models Using Goodput",
         "authors": "Xiaoxuan Liu, Cade Daniel, Langxiang Hu, Woosuk Kwon, Zhuohan Li, Xiangxi Mo, Alvin Cheung, Zhijie Deng, Ion Stoica, Hao Zhang",
@@ -14,7 +38,7 @@
     {
         "title": "AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models",
         "authors": "Zihao Zeng, Yibo Miao, Hongcheng Gao, Hao Zhang, Zhijie Deng",
-        "venue": "Preprint 2024",
+        "venue": "EMNLP 2024",
         "pdf": "https://arxiv.org/pdf/2406.13233",
         "code": "",
         "presentation": "",
@@ -38,7 +62,7 @@
     {
         "title": "Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length",
         "authors": "Xuezhe Ma*, Xiaomeng Yang*, Wenhan Xiong, Beidi Chen, Lili Yu, Hao Zhang, Jonathan May, Luke Zettlemoyer, Omer Levy, Chunting Zhou*",
-        "venue": "Preprint 2024",
+        "venue": "NeurIPS 2024",
         "pdf": "https://arxiv.org/pdf/2404.08801",
         "code": "https://github.com/XuezheMax/megalodon",
         "presentation": "",