Author

Wu-Jun Li

h-index 1 View on Semantic Scholar

We have 1 of 4 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Automated Tensor Scheduling for Hybrid CPU-GPU LLM Inference on Consumer Devices

ATSInfer combines static tensor placement with load-aware dynamic transfer and introduces asynchronous CPU-GPU coordination to efficiently schedule hardware storage, data movement, and computation across heterogeneous backends and can substantially improve the user experience of local LLM deployment on personal consumer devices.

Yangyijian Liu, Hong-Yi Ye, Ming-Yang Li et al. · arXiv.org · 0 citations