2 papers
cs.DC2026
Sample-Guided Exact Top-K Selection for Long-Context Sparse Attention
Siran Liu, Yang Xue, Theo Tang +11
Sparse attention bounds downstream attention work by retaining a fixed-size subset of indexed tokens, but its standalone exact Top- stage must still process materialized score r…
cs.AR2026
FlashAccel: Leveraging High-Bandwidth Flash (HBF) for High-Throughput LLM Inference
Xinyu Wang, Yalong Xue, Xiaotian Sun +5
Large language model (LLM) inference is increasingly limited by the capacity of High-Bandwidth Memory (HBM) in GPUs, as model weights and KV cache grow rapidly. High-Bandwidth Flas…