Harry Dong

2 papers · 2024–2025 · 1 conference · across top CS/AI conferences

Conferences

ICML (2)

Top co-authors

Beidi Chen (2) Yuejie Chi (2) Xin Liu (1) Wenlei Bao (1) Zhenyu Zhang (1) Xinyu Yang (1) Ningxin Zheng (1) Zhangyang Wang (1) Size Zheng (1) Li-Wen Chang (1)

Papers

ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference ICML 2025

Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference ICML 2024