xla
xla copied to clipboard
openxla
A machine learning compiler for GPUs, CPUs, and ML accelerators
![copybara-service[bot] avatar](https://avatars.githubusercontent.com/in/44061?v=4 "copybara-service[bot] avatar"){kind=avatar}
Use absl::Status instead of xla::Status now that they're identical.
[XLA:GPU] [XLA:GPU] Clang-tidy fixes for xla/service/gpu/gpu_hlo_schedule.cc
This enables activation offloading automatically on GPU through HLO Rematerialization. There is one xla flag needed to trigger rematerialization offloading: 1. A bool to enable host memory offloading. It's false...
Move `tsl/framework` to `xla/tsl/framework`
allow a tpu pjrt client to be created with extra options
Reverts d7a758b212fe9f9d2ad6fa58ec0e4ad5a1c53ead