2 papers
cs.DC2026
Guess-Verify-Refine: Data-Aware Top-K for Sparse-Attention Decoding on Blackwell via Temporal Correlation
Long Cheng, Ritchie Zhao, Timmy Liu +7
Sparse-attention decoders rely on exact Top-K selection to choose the most important key-value entries for each query token. In long-context LLM serving, this Top-K stage runs once…
cs.CL2025
RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression
Payman Behnam, Yaosheng Fu, Ritchie Zhao +3
Transformer-based Large Language Models rely critically on the KV cache to efficiently handle extended contexts during the decode phase. Yet, the size of the KV cache grows proport…