Build tracy by default in the Python runtime packages. (#14639) This is accomplished by: * Re-organizing the native dependencies under `iree._runtime_libs` and `iree._runtime_libs_tracy`, which can co-exist in the same wheel. * Have `runtime/setup.py` do an additional CMake build for `_runtime_libs_tracy` if the env var `IREE_RUNTIME_BUILD_TRACY=ON`. * Re-mash `setup.py` to make it happy with the new layout and make everything optional. * Split the package prefixes for the source and built directories. * Move generated version.py to the built _runtime_libs package and trampoline from `iree.runtime.version` to preserve the API. * Modify the `_binding.py` loader (loaded at `iree.runtime` init time) to dynamically switch its backing runtime based on the value of the environment variable `IREE_PY_RUNTIME`, which can be `default` or `tracy`. * Rework all of the `__main__.py` wrappers (for `iree-run-module` and such) to use the runtime library path found in the previous step. This can be improved in the future to eliminate more binary size duplication by adopting a busybox-like strategy as used on the compiler (would also be a good time to enable LTO, clang, and debug symbols). As-is, this ~doubles the size to about 7MiB, which is acceptable given the usability benefit. I expect with such re-organizations, we can get it to roughly half of its size prior to this change (1/4 after).
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.