Repository navigation
Test: Do not accept an engine error as a streamed reply - #147
Merged
Merged
Conversation
test_streams_tokens_then_eos only checked that some text arrived before <EOS>, so it passed on mps where every engine call failed: the model layer turns the failure into an 'ERROR:' message frame. It now rejects that.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
test_streams_tokens_then_eospassed on torchnative 0.1.0b4 + mps although every engine call failed (the reply was anERROR:frame). It now asserts the reply contains noERROR:marker. Real-model test: verified by CI on SmolLM2.Closes #146