server : add system_fingerprint to chat/completion #10917
+25
−15
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Outdated suggestions cannot be applied.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.
While working with compatible between llama.cpp and HF inference library, I noticed that llama.cpp is missing
system_fingerprint
compared the OAI compat response.While this field is not required (and indeed we can remove the check for this field from HF library), I think it's more useful to implement it here in llama.cpp and return the build number (+ the commit hash).
This should be useful for downstream projects to know if the current server is up-to-date or not. We can additionally display this on the webui in the future.
For details of OAI API, see: https://platform.openai.com/docs/api-reference/chat/object