3 points | by r2ob 9 hours ago
2 comments
RIS-Kernel: A Model-Agnostic Architecture for Long-Context LLM Inference via Sparse Attention
RIS reduces self-attention complexity to $O(N \log N)$ using sparse stochastic geometry that fits within commodity memory limits
https://www.nature.com/articles/s41598-026-59160-z
RIS-Kernel: A Model-Agnostic Architecture for Long-Context LLM Inference via Sparse Attention
RIS reduces self-attention complexity to $O(N \log N)$ using sparse stochastic geometry that fits within commodity memory limits
https://www.nature.com/articles/s41598-026-59160-z