7 papers
RAG-Stack: Co-Optimizing RAG Serving Performance and Quality
Haiqiang Zhang, Yuanqing Lei, Wanting Li +2
Retrieval-augmented generation (RAG), which augments large language model (LLM) generation with information retrieved from databases, has become a widely used approach for knowledg…
ROSA: A Robotics Foundation Model Serving System for Robot Factories
Wenqi Jiang, Jason Clemons, Rowland O'Flaherty +5
Robotics foundation models (RFMs) are making general-purpose robots increasingly practical for factory deployments. While RFM serving systems are central to this vision, existing s…
HEXGEN-FLOW: Optimizing LLM Inference Request Scheduling for Agentic Text-to-SQL
You Peng, Youhe Jiang, Wenqi Jiang +2
Recent advances in agentic large language models (LLMs) have substantially improved Text-to-SQL, enabling users without database expertise to query databases intuitively. However,…
How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perf
Wenqi Jiang, Jason Clemons, Karu Sankaralingam +1
Vision-Language-Action (VLA) models have recently demonstrated impressive capabilities across various embodied AI tasks. While deploying VLA models on real-world robots imposes str…
Controlled Self-Evolution for Algorithmic Code Optimization
Tu Hu, Ronghao Chen, Shuo Zhang +9
Self-evolution methods enhance code generation through iterative "generate-verify-refine" cycles, yet existing approaches suffer from low exploration efficiency, failing to discove…
RAG-Stack: Co-Optimizing RAG Quality and Performance From the Vector Database Perspective
Wenqi Jiang
Retrieval-augmented generation (RAG) has emerged as one of the most prominent applications of vector databases. By integrating documents retrieved from a database into the prompt o…