llama-server: friendlier error msg when ctx < input #18174
+17
−3
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
This PR adds formatted strings to the server's send_error function
ngxson
reviewed
Dec 18, 2025
Collaborator
|
One of the test need to be updated too |
ngxson
reviewed
Dec 18, 2025
| send_error(slot, "input is larger than the max context size. skipping", ERROR_TYPE_EXCEED_CONTEXT_SIZE); | ||
| send_error( | ||
| slot, | ||
| string_format( |
Collaborator
There was a problem hiding this comment.
just wondering if this is actually needed, because the info about n_tokens and n_ctx already included inside the response (ad dedicated fields, not in the error message)
Edit: hmm ok the CLI doesn't read these fields. I think we can merge this quick fix and I'll refactor this error handling later
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
This PR adds formatted strings to the server's send_error function
I was testing out the new cli and I thought that these might be more helpful to debug when reading too large an input