Kan Zhu

3 papers · 2024–2025 · 3 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (3) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer

Conferences

ICLR (1) ICML (1) OSDI (1)

Top co-authors

Baris Kasikci (3) Keisuke Kamahori (2) Yile Gu (2) Yilong Zhao (2) Tian Tang (2) Liangyu Zhao (1) Stephanie Wang (1) Song Han (1) Chien-Yu Lin (1) Arvind Krishnamurthy (1)

Keywords

intra-device parallelism (1) nano-batch scheduling (1) gpu throughput (1) resource overlapping (1) execution time optimization (1)

Papers

Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models ICLR 2025

NanoFlow: Towards Optimal Large Language Model Serving Throughput OSDI 2025

QUEST: Query-Aware Sparsity for Efficient Long-Context LLM Inference ICML 2024