PiLLM: Resource-efficient LLM Inference Using Workload Prediction

Jan 1, 2026·

Yunqian Fan

,

Shihao Bai

Ruihao Gong

Ruihao Gong

📧 Corresponding Author

,

Zaijun Wang

,

Rui Fan

📧 Corresponding Author

· 0 min read

Type

Conference paper

Publication

Proceedings of the 21st European Conference on Computer Systems (EuroSys)

Last updated on Jan 1, 2026

Ruihao Gong

Authors

← LLMC+: Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkit Jun 1, 2026

TokenSim: Enabling Hardware and Software Exploration for Large Language Model Inference Systems Jan 1, 2026 →