2 papers
cs.IR2026
Self-Indexing Attention for Compression-Compatible Sparse Long-Context LLM Inference
Xu Yang, Jiapeng Zhang, Zhangke +6
Sparse long-context inference requires efficient token retrieval in both prefill and decode. Existing methods often use different retrieval strategies for the two stages, preventin…
cs.DC2025
MultiPath Memory Access: Breaking Host-GPU Bandwidth Bottlenecks in LLM Services
Lingfeng Tang, Daoping Zhang, Junjie Chen +6
Host-GPU data movement has become a latency-critical bottleneck in LLM serving, surfacing in common paths such as model-weight movement and KV cache offload/fetch. Today, each host…