no code implementations • 1 Nov 2023 • Ruihang Lai, Junru Shao, Siyuan Feng, Steven S. Lyubomirsky, Bohan Hou, Wuwei Lin, Zihao Ye, Hongyi Jin, Yuchen Jin, Jiawei Liu, Lesheng Jin, Yaxing Cai, Ziheng Jiang, Yong Wu, Sunghyun Park, Prakalp Srivastava, Jared G. Roesch, Todd C. Mowry, Tianqi Chen
Dynamic shape computations have become critical in modern machine learning workloads, especially in emerging large language models.
no code implementations • 17 May 2023 • Pratik Fegade, Tianqi Chen, Phillip B. Gibbons, Todd C. Mowry
Dynamic control flow is an important technique often used to design expressive and efficient deep learning computations for applications such as text parsing, machine translation, exiting early out of deep models and so on.
no code implementations • 8 Feb 2023 • Siyuan Chen, Pratik Fegade, Tianqi Chen, Phillip B. Gibbons, Todd C. Mowry
Further, batching puts strict restrictions on memory adjacency and can lead to high data movement costs.
no code implementations • 19 Oct 2021 • Pratik Fegade, Tianqi Chen, Phillip B. Gibbons, Todd C. Mowry
There is often variation in the shape and size of input data used for deep learning.
no code implementations • 2 Nov 2020 • Pratik Fegade, Tianqi Chen, Phillip B. Gibbons, Todd C. Mowry
Optimizing deep learning models is generally performed in two steps: (i) high-level graph optimizations such as kernel fusion and (ii) low level kernel optimizations such as those found in vendor libraries.