xla
xla copied to clipboard
openxla
A machine learning compiler for GPUs, CPUs, and ML accelerators
Integrate LLVM at llvm/llvm-project@485237413577 Updates LLVM usage to match [485237413577](https://github.com/llvm/llvm-project/commit/485237413577)
![copybara-service[bot] avatar](https://avatars.githubusercontent.com/in/44061?v=4 "copybara-service[bot] avatar"){kind=avatar}
PR #17754: [NFC] Extract common builder code into hlo_creation_utils Imported from GitHub PR https://github.com/openxla/xla/pull/17754 Added `XlaComputationToHloComputation` helper function to `hlo_creation_utils` and replace the uses. Copybara import of the project: --...
PR #17858: [ROCm] Fix build brake caused by missing dso_loader.h includes Imported from GitHub PR https://github.com/openxla/xla/pull/17858 The issue was introduced here -> https://github.com/openxla/xla/commit/b30b420510a89caa6ce9ae12c16add7e416e9034#diff-923ec2612240244a60ae28c17f798a7daeccbab84a8e9de9efd7ba96c311c763L115 Some of the ROCm files need `dso_loader.h`....
Internal change: fix non-copyable object from TF_ASSIGN_OR_RETURN
[XLA:GPU] Support partially pipelined async send recv ops This is needed for pipeline parallelism on GPU where the send/recv operations are issued in one loop iteration and completed in the...
Always use provided tmpdir if specified by user
[HLO Componentization] Create hlo/parser sub-component (Phase II). This CL takes care of 1. Migrating external projects dependencies from xla/service --> xla/hlo/parser Phase I takes care of 1. Migrating xla/service -->...
Added `XlaComputationToHloComputation` helper function to `hlo_creation_utils` and replace the uses.
