Media Summary: Ying Chen and Harini Sridhar explain how to take advantage of Naums Mogers and Jevin Jiang talk about how compilation of Pallas kernels work for TPU TensorCores and Minho Ryu, a Google Developer Expert in AI, talks about how you can contribute to the
Sparsecore Offloading Jax Openxla Devlab Fall 2025 - Detailed Analysis & Overview
Ying Chen and Harini Sridhar explain how to take advantage of Naums Mogers and Jevin Jiang talk about how compilation of Pallas kernels work for TPU TensorCores and Minho Ryu, a Google Developer Expert in AI, talks about how you can contribute to the Anxhelo Xhebraj introduces JaxPP, a library that enables MPMD training. Yu-Hang Tang from Nvidia talks about Post-training in Ihor Indyk introduces Grain, a Python library for data processing and loading for
Jiaxin Cao shows off how to execute async PjRT on GPU. Sharad Vikram explains how to use Pallas to make your custom kernels on TPUs go fast! Matthew Johnson, Principal Scientist at Google, delivers the Keynote address at the Zeev Melumian talks about how to combine PyTorch and
