Xiangrui Yu
Source-listed: RD · PaddlePaddle, Baidu
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUsSaved credit: Maintainer · 2025Explore people connected to this work →
- ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless CompressionSaved credit: Contributor · 2026Explore people connected to this work →
- DynSpAttn: Efficient Attention via Dual-Side Dynamic Sparsity on Sparse Tensor CoresSaved credit: Contributor · 2026Explore people connected to this work →
- ROME: Maximizing GPU Efficiency for All-Pairs Shortest Path via Taming Fine-Grained IrregularitiesSaved credit: Contributor · 2026Explore people connected to this work →
- Balancing Computation and Communication in Distributed Sparse Matrix-Vector MultiplicationSaved credit: Contributor · 2023Explore people connected to this work →