Point at a runtime you already have¶
You have ONNX Runtime installed — from a distribution package, a vendor build, or a compile of your own — and you want the resolver to use it rather than fetch one.
Pass the path¶
That is the whole answer. An explicit path outranks every other source and short-circuits the rest of the chain: no cache lookup, no network, no index.
Wire it to configuration¶
Pass the configured value through unconditionally rather than branching on it. An empty string is the documented way to say decide for me, so the branch you would write is one the resolver already contains:
Wire it to the environment¶
In a container image that already ships the runtime, export the path once and read it in one place:
Unset, os.Getenv returns "" and the resolver falls through to its normal
order — so the same binary works inside the image and on a developer's laptop
without a second code path.
The path is not checked¶
A path you pass is returned as given, even if nothing is there. This is deliberate. The alternative — falling back to the channel when your path does not resolve — means a machine you have configured quietly runs a different runtime from the one you specified, and the mismatch shows up as an inference result rather than an error.
If your path is wrong you get the dynamic loader's complaint about your path, which names the file you meant.
When there is no published build¶
This is the remedy ErrNoPlatformBuild points at. Upstream dropped macOS Intel
between 1.23.0 and 1.26.0, so a machine that once resolved a runtime from the
channel gets nothing at a later version. An explicit path is how that machine
keeps working — see platform builds.