From the 1 of 6 linked papers with an AI index.
6 papers
LiteTopK: Exploiting the Curse of Dimensionality for a Fused Indexer-TopK Kernel in Long-Context Sparse Attention
Ziqi Yin, Jianyang Gao, Peiqi Yin +2
The paper introduces LiteTopK, a fused GPU kernel that combines indexing and top‑k selection for sparse attention by exploiting the concentration of distances in high‑dimensional s…
Revisiting RaBitQ and TurboQuant: A Symmetric Comparison of Methods, Theory, and Experiments
Jianyang Gao, Yutong Gou, Yuexuan Xu +5
This technical note revisits the relationship between RaBitQ and TurboQuant under a unified comparison framework. We compare the two methods in terms of methodology, theoretical gu…
GPU-Native Approximate Nearest Neighbor Search with IVF-RaBitQ: Fast Index Build and Search
Jifan Shi, Jianyang Gao, James Xia +2
Approximate nearest neighbor search (ANNS) on GPUs is gaining increasing popularity for modern retrieval and recommendation workloads that operate over massive high-dimensional vec…
mHC-lite: You Don't Need 20 Sinkhorn-Knopp Iterations
Yongyi Yang, Jianyang Gao
Hyper-Connections (HC) generalizes residual connections by introducing dynamic residual matrices that mix information across multiple residual streams, accelerating convergence in…
RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm
Yongyi Yang, Jianyang Gao, Wei Hu
Post-training Quantization (PTQ) has become a widely used technique for improving inference efficiency of large language models (LLMs). However, existing PTQ methods generally suff…
DEG: Efficient Hybrid Vector Search Using the Dynamic Edge Navigation Graph
Ziqi Yin, Jianyang Gao, Pasquale Balsebre +2
Bimodal data, such as image-text pairs, has become increasingly prevalent in the digital era. The Hybrid Vector Query (HVQ) is an effective approach for querying such data and has…