server : Add verbose output to OAI compatible chat endpoint. #12246
+5
−0
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
|
I can merge only if you can fix the CI |
github-actions
bot
added
script
|
Ok, let me try to figure out how to run the CI locally. |
mglambda
force-pushed
the
server-verbose-result-oaicompat-stream
branch
from
7a54db2 to
46cca0d
Compare
github-actions
bot
added
documentation
mglambda
force-pushed
the
server-verbose-result-oaicompat-stream
branch
from
46cca0d to
35d63f1
Compare
|
Ok I saw the whitespace problem. Hope things are fine now. Baby's first pr. |
Add verbose output to server_task_result_cmpl_final::to_json_oaicompat_chat_stream, making it conform with server_task_result_cmpl_final::to_json_oaicompat_chat, as well as the other to_json methods.
mglambda
force-pushed
the
server-verbose-result-oaicompat-stream
branch
from
35d63f1 to
d261b13
Compare
ngxson
approved these changes
Mar 23, 2025
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Outdated suggestions cannot be applied.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.
I noticed that the /chat/completions and /v1/completions endpoints do not return the "__verbose" field in the final server response when running llama-server with -lv 10 and streaming enabled. This is inconsistent with the non-streaming behaviour of those endpoints.
This pr adds verbose output to server_task_result_cmpl_final::to_json_oaicompat_chat_stream, making it conform with server_task_result_cmpl_final::to_json_oaicompat_chat, as well as the other to_json methods.
This was motivated by me wanting to know the tokens_cached in streaming mode on those endpoints. If anyone has another way of doing that, preferably without verbose mode, I'd be very interested.