HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration

Jan 1, 2025·

Yushi Huang

,

Zining Wang

Ruihao Gong

📧 Corresponding Author

,

Jing Liu

,

Xinjie Zhang

,

Jinyang Guo

,

Xianglong Liu

,

Jun Zhang

· 0 min read

Cite

Authors

Ruihao Gong

---

← DA-KD: Difficulty-Aware Knowledge Distillation for Efficient Large Language Models Jan 1, 2025

Hierarchical Balance Packing: Towards Efficient Supervised Fine-tuning for Long-Context LLM Jan 1, 2025 →