fix(onnx): make provider_options optional in OnnxRuntimeModel._from_pretrained (#13653)#13667
Open
Anai-Guo wants to merge 1 commit intohuggingface:mainfrom
Open
fix(onnx): make provider_options optional in OnnxRuntimeModel._from_pretrained (#13653)#13667Anai-Guo wants to merge 1 commit intohuggingface:mainfrom
Anai-Guo wants to merge 1 commit intohuggingface:mainfrom
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Problem
Fixes Issue 1 of #13653.
OnnxRuntimeModel._from_pretrained()callskwargs.pop("provider_options")without a default in both the local-directory and Hub branches. Pipeline loading happens to passprovider_options=None, so the failure is hidden in that path. Direct use of the public helper, however, raisesKeyErrorbefore any loading happens.Reproduction
Fix
Pass a
Nonedefault to bothkwargs.pop("provider_options", None)calls. The downstreamOnnxRuntimeModel.load_model()already normalisesNone → [](lines 86-89), so the new default keeps existing pipeline-loading behaviour identical and unblocks directfrom_pretrained()calls.Notes
onnx_utils.py.OnnxRuntimeModel.from_pretrained()and lists this in the meta-issue test-coverage section, which felt like an explicit follow-up rather than something to slip into this surgical fix. Happy to add a fast unit test if preferred.🤖 Generated with Claude Code