From the 1 of 8 linked papers with an AI index.
8 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…
LiveServe: Interaction-Aware Serving for Real-Time Omni-Modal LLMs
Xiangyu Zhi, Peiqi Yin, Sheng Guan +3
Realtime omni-modal LMs support speech-centric conversations where users stream inputs, hear generated audio, and interrupt freely. Existing Omni-LM serving systems still rely on t…
ScaleGANN: Accelerate Large-Scale ANN Indexing by Cost-effective Cloud GPUs
Lan Lu, Peiqi Yin, Isaac Yang +5
Graph-based ANNS algorithms have gained increasing research interest and market adoption due to their efficiency and accuracy in retrieval. Existing approaches primarily rely on CP…
vLLM-Omni: Fully Disaggregated Serving for Any-to-Any Multimodal Models
Peiqi Yin, Jiangyun Zhu, Han Gao +13
Any-to-any multimodal models that jointly handle text, images, video, and audio represent a significant advance in multimodal AI. However, their complex architectures (typically co…
SparseServe: Unlocking Parallelism for Dynamic Sparse Attention in Long-Context LLM Serving
Qihui Zhou, Peiqi Yin, Pengfei Zuo +1
Serving long-context LLMs is costly because attention computation grows linearly with context length. Dynamic sparse attention algorithms (DSAs) mitigate this by attending only to…
Gorgeous: Revisiting the Data Layout for Disk-Resident High-Dimensional Vector Search
Peiqi Yin, Xiao Yan, Qihui Zhou +6
Similarity-based vector search underpins many important applications, but a key challenge is processing massive vector datasets (e.g., in TBs). To reduce costs, some systems utiliz…