| commit | 567a4490d018ebcc31cb8f9cd3648efb176c6c3d | [log] [tgz] |
|---|---|---|
| author | Scott Todd <scott.todd0@gmail.com> | Fri Feb 16 13:02:57 2024 -0800 |
| committer | GitHub <noreply@github.com> | Fri Feb 16 21:02:57 2024 +0000 |
| tree | e7d9ff4ae42e52de7de9d49192d085ab7a4fa427 | |
| parent | 0c540db090d4aa55211e706b13f88014b8c3c7d6 [diff] |
Only run benchmark workflows when requested. (#16439) Progress on https://github.com/openxla/iree/issues/16431. The `build_e2e_test_artifacts` job produces artifacts used for benchmarking but it has been also providing test coverage that the programs in the benchmark suite can be compiled correctly. That test coverage would be a better fit for a test job like `test_gpu` (ci.yml) or `regression_test_cpu` (pkgci.yml). As it is now, that job is building multiple very similar configurations and it then uploads those files to the cloud (to the tune of 70-130GB per CI run). This also adds back coverage that was missing from `test_benchmark_suites`. Those tests should be migrated to another workflow not connected to benchmarks so they can be ran and debugged in isolation. This setup is too brittle and complex.
IREE (Intermediate Representation Execution Environment, pronounced as “eerie”) is an MLIR-based end-to-end compiler and runtime that lowers Machine Learning (ML) models to a unified IR that scales up to meet the needs of the datacenter and down to satisfy the constraints and special considerations of mobile and edge deployments.
See our website for project details, user guides, and instructions on building from source.
IREE is still in its early phase. We have settled down on the overarching infrastructure and are actively improving various software components as well as project logistics. It is still quite far from ready for everyday use and is made available without any support at the moment. With that said, we welcome any kind of feedback on any communication channels!
See our website for more information.
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.