논문 리뷰
1.HAT: Hardware-Aware Transformers for Efficient Natural Language Processing
저자 Hanrui Wang, Zhanghao Wu, Zhijian Liu, Han Cai, Ligeng Zhu, Chuang Gan, Song Han arXiv https://arxiv.org/abs/2005.14187 Github https:
2024년 11월 25일
2.Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs
원문 ICML: https://icml.cc/virtual/2025/poster/43564 Openreview: https://openreview.net/forum?id=xnEv5pq4cB ArXiv: https://arxiv.o
2025년 9월 24일