6 papers
ObjectCache: Layerwise Object-Storage Retrieval for KV Cache Reuse
Yu Zhu, Aditya Dhakal, Yunming Xiao +2
Prefix KV caching has become a key mechanism in LLM serving: it reduces time to first token (TTFT) by avoiding redundant computation across requests that share a prefix (i.e., the…
Accelerating Recommender Model ETL with a Streaming FPGA-GPU Dataflow
Yu Zhu, Wenqi Jiang, Piyumi Jasin Pathiranage +2
The real-time performance of recommender models depends on the continuous integration of massive volumes of new user interaction data into training pipelines. While GPUs have scale…
Fast Graph Vector Search via Hardware Acceleration and Delayed-Synchronization Traversal
Wenqi Jiang, Hang Hu, Torsten Hoefler +1
Vector search systems are indispensable in large language model (LLM) serving, search engines, and recommender systems, where minimizing online search latency is essential. Among v…
Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models
Wenqi Jiang, Marco Zeller, Roger Waleffe +2
A Retrieval-Augmented Language Model (RALM) combines a large language model (LLM) with a vector database to retrieve context-specific knowledge during text generation. This strateg…
SwiftSpatial: Spatial Joins on Modern Hardware
Wenqi Jiang, Oleh-Yevhen Khavrona, Martin Parvanov +1
Spatial joins are among the most time-consuming spatial queries, remaining costly even in parallel and distributed systems. In this paper, we explore hardware acceleration for spat…
RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving
Wenqi Jiang, Suvinay Subramanian, Cat Graves +3
Retrieval-augmented generation (RAG), which combines large language models (LLMs) with retrievals from external knowledge databases, is emerging as a popular approach for reliable…