11 papers
Simple is Better: Multiplication May Be All You Need for LLM Request Scheduling
Dingyan Zhang, Jinbo Han, Kaixi Zhang +6
High-quality LLM request scheduling requires meeting two key objectives: ensuring the routed instance has KVCache to accelerate request execution, and ensuring that the workload is…
A Few GPUs, A Whole Lotta Scale: Faithful LLM Training Emulation with PrismLLM
Shaoke Xi, ChonLam Lao, Boyi Jia +11
Large language model (LLM) training today runs on clusters spanning thousands of GPUs. While this scale enables rapid model advances, developing, debugging, and performance-tuning…
Efficient Vector Search in the Wild: One Model for Multi-K Queries
Yifan Peng, Jiafei Fan, Xingda Wei +7
Learned top-K search is a promising approach for serving vector queries with both high accuracy and performance. However, current models trained for a specific K value fail to gene…
Revisiting Graph Analytics Benchmark
Lingkai Meng, Yu Shao, Long Yuan +7
The rise of graph analytics platforms has led to the development of various benchmarks for evaluating and comparing platform performance. However, existing benchmarks often fall sh…
Qwen3Guard Technical Report
Haiquan Zhao, Chenhan Yuan, Fei Huang +40
As large language models (LLMs) become more capable and widely used, ensuring the safety of their outputs is increasingly critical. Existing guardrail models, though useful in stat…
OSS-UAgent: An Agent-based Usability Evaluation Framework for Open Source Software
Lingkai Meng, Yu Shao, Long Yuan +6
Usability evaluation is critical to the impact and adoption of open source software (OSS), yet traditional methods relying on human evaluators suffer from high costs and limited sc…