CURRENTF/SparseEngine

RIS-Kernel: A Model-Agnostic Architecture for Long-Context LLM Inference via Sparse Attention

Sparse Decoupled Attention for Efficient Long-Context LLM Inference

[NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while maintaining accuracy.

[VLDB 26, NeurIPS 25] Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.

[ICML 26 Spotlight, NeurIPS 25 @ ER] Long-Context Modeling with Dynamic Hierarchical Sparse Attention for Memory-Constrained LLM Inference

eLLM: Run Long-Horizon Inference Faster on CPUs Than on GPUs

Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention

[NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning