Predicting LLM Inference Latency: A Roofline-Driven ML Method
- Saki Imai
- Rina Nakazawa
- et al.
- 2024
- NeurIPS 2024
In 2014, I earned a Bachelor of Engineering degree, B.Eng. (Computer Engineering), from Chulalongkorn University, Thailand.
Back then, I worked on Network Security on Mobile Adhoc Networks in expecting disaster situations.
In 2017 and 2020, I have completed my Master's and Doctoral Degree in Information Science and Technology from Osaka University, Japan.
My research theme was a Real-time Data Stream Processing Technology towards an era of Big Data in IoT. In particular, I have focused on a Fully-distributed Scheme Solution that leverages the concept of self-sustaining IoT, where any devices collaborate themselves on sensing, processing, and acting regarding shared human-defined recipes. My area of interest also includes data quality evaluation, delayed tolerant networks, and data sharing encouragement.
From April, 2020, I have started my journey as a researcher in IBM Research Japan Team for performance optimization work on Hybrid Cloud.
The research project has highlighted the challenges of evaluating, enhancing, and optimizing services with modular architectures distributing on the cloud and expecting an automatic recommendation for upgrading service-providing efficiency and value.
Technical Program Committee
Organization Committee
Session Chair