733d71db88
Imported from GitHub PR https://github.com/openxla/xla/pull/19528 Observed in saxml workload that sharing the same command buffer cmd type (CONDITIONALS) for WHILE and CONDITIONAL command over kill the lowering opportunities. Many cases could allow CONDITIONAL instruction to lower into command buffer, while WHILE is not possible. This PR uses separate command buffer cmd type flag for CONDITIONAL and WHILE instructions when user specifies the type to lowering. Copybara import of the project: -- 4d62fb512995e2fc6e9077a1b3251a6754c866ca by Shawn Wang <shawnw@nvidia.com>: use separte command buffer cmd flag for conditional and loop Merging this change closes #19528 PiperOrigin-RevId: 698729891 |
||
|---|---|---|
| .. | ||
| .github | ||
| .kokoro | ||
| build_tools | ||
| docs | ||
| third_party | ||
| tools | ||
| xla | ||
| .bazelrc | ||
| .bazelversion | ||
| .clang-format | ||
| .clang-tidy | ||
| .gitignore | ||
| BUILD.bazel | ||
| CONTRIBUTING.md | ||
| LICENSE | ||
| opensource_only.files | ||
| README.md | ||
| requirements_lock_3_11.txt | ||
| warnings.bazelrc | ||
| workspace0.bzl | ||
| workspace1.bzl | ||
| workspace2.bzl | ||
| workspace3.bzl | ||
| workspace4.bzl | ||
| WORKSPACE | ||
XLA
XLA (Accelerated Linear Algebra) is an open-source machine learning (ML) compiler for GPUs, CPUs, and ML accelerators.
The XLA compiler takes models from popular ML frameworks such as PyTorch, TensorFlow, and JAX, and optimizes them for high-performance execution across different hardware platforms including GPUs, CPUs, and ML accelerators.
Get started
If you want to use XLA to compile your ML project, refer to the corresponding documentation for your ML framework:
If you're not contributing code to the XLA compiler, you don't need to clone and build this repo. Everything here is intended for XLA contributors who want to develop the compiler and XLA integrators who want to debug or add support for ML frontends and hardware backends.
Contribute
If you'd like to contribute to XLA, review How to Contribute and then see the developer guide.
Contacts
- For questions, contact the maintainers - maintainers at openxla.org
Resources
Code of Conduct
While under TensorFlow governance, all community spaces for SIG OpenXLA are subject to the TensorFlow Code of Conduct.