Christina Zhang

Christina (Jingrong) Zhang is from the Devtech Compute team of NVIDIA, where she focuses on accelerating the Top-K part widely used in various deep learning models. She graduated from the Chinese Academy of Sciences, Institute of Computing Technology. During her Ph.D. period, she focused on using CUDA and deep learning to optimize Cryo-EM image processing. After joining NVIDIA, she used CUDA and CUBLAS to accelerate the inference process of XLNet.
Avatar photo

Posts by Christina Zhang

Data Science

Accelerated Vector Search: Approximating with RAPIDS RAFT IVF-Flat

Performing an exhaustive exact k-nearest neighbor (kNN) search, also known as brute-force search, is expensive, and it doesn’t scale particularly well to... 15 MIN READ