Do not process prompts containing binary data for escapes #15302
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
Adopts code from ikawrakow/ik_llama.cpp#33 to fix the broken llama-perplexity.
kallewoof
force-pushed
the
202508-binary-prompts
branch
from
0f99ce7 to
b9c1aef
Compare
Contributor
|
I'm not an authority on this subject, but as I understand it, llama.cpp is hesitant to accept code that's taken from ikawrakow due to some past conflicts. Just FYI |
Contributor
Author
I kind of figured. But as it stands the code is broken and it's a pain to have to juggle llamas on a per task basis. And the change is really very trivial. I could rewrite it with my own hands if that is preferred, but I doubt it would come out much different from the original. |
Contributor
Author
|
After adjusting arguments I'm no longer sure this patch is necessary so closing for now. |
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Outdated suggestions cannot be applied.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.
Adopts code from ikawrakow/ik_llama.cpp#33 to fix the broken llama-perplexity.
Fixes #9316.