Zhan-Wei Wu

According to our database, Zhan-Wei Wu authored at least 4 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

MoE-Pipe: A Pipelined MoE Model Loading Framework for Reducing the Cold Start Delays in Serverless Inference.

Zhan-Wei Wu, Chih-Tai Tsai, Sao-Hsuan Lin, Yi-Syuan Ke, Jerry Chou

Proceedings of the 16th International Conference on Cloud Computing and Services Science, 2026

NIKA: Optimal KV Cache Transfer for Minimizing the Latency of Disaggregated LLM Inference.

Chih-Tai Tsai, Zhan-Wei Wu, Yi-Syuan Ke, Sao-Hsuan Lin, Jerry Chou

Proceedings of the 16th International Conference on Cloud Computing and Services Science, 2026

HybridServe: Stall-Free Distributed Disaggregated LLM Inference with Hybrid KVCache Buffering.

Yi-Syuan Ke, Zhan-Wei Wu, Chih-Tai Tsai, Sao-Hsuan Lin, Jerry Chou

Proceedings of the 16th International Conference on Cloud Computing and Services Science, 2026

2024

CacheFlow: Enhancing Data Flow Efficiency in Serverless Computing by Local Caching.

Yi-Syuan Ke, Zhan-Wei Wu, Chih-Tai Tsai, Sao-Hsuan Lin, Jerry Chou

Proceedings of the 14th International Conference on Cloud Computing and Services Science, 2024