APA (7th ed.) Citation

Zhuge, X., Shen, X., Wang, Z., Dang, F., Ding, X., Li, D., . . . Yang, Z. (2025). SpecOffload: Unlocking Latent GPU Capacity for LLM Inference on Resource-Constrained Devices.

Chicago Style (17th ed.) Citation

Zhuge, Xiangwen, Xu Shen, Zeyu Wang, Fan Dang, Xuan Ding, Danyang Li, Yahui Han, Tianxiang Hao, and Zheng Yang. SpecOffload: Unlocking Latent GPU Capacity for LLM Inference on Resource-Constrained Devices. 2025.

MLA (9th ed.) Citation

Zhuge, Xiangwen, et al. SpecOffload: Unlocking Latent GPU Capacity for LLM Inference on Resource-Constrained Devices. 2025.