improved handling of LLM errors, do not retry if already began #1298
Conversation
This file contains 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
LLM could timeout after producing initial tokens, in those cases the inference request should not be retries. the error would be propagated to the caller (PipelineAgent), who could handle it similarly to an interruption. (i.e. flagging it and performing new inference)
🦋 Changeset detectedLatest commit: fdeee56 The changes in this PR will be included in the next version bump. This PR includes changesets to release 3 packages
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
theomonnom
approved these changes
Dec 25, 2024
This was referenced Dec 25, 2024
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Outdated suggestions cannot be applied.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.
LLM could timeout after producing initial tokens, in those cases the inference request should not be retried. the error would be propagated to the caller (PipelineAgent), who could handle it similarly to an interruption. (i.e. flagging it and performing new inference)