LLM Inference Unveiled: Survey and Roofline Model Insights Zhihang Yuan Yuzhang Shang Yang Zhou Zhen Dong Zhe Zhou ...Yong Jae Lee Yan Yan Beidi Chen Guangyu Sun Kurt Keutzer |
Understanding the Training Speedup from Sampling with Approximate LossesInternational Conference on Machine Learning (ICML), 2024 |