logs : reduce#23021
Merged
Merged
Conversation
ggerganov
commented
May 13, 2026
Comment on lines
-752
to
-754
| if (!is_resume) { | ||
| mtmd_helper_log_set(common_log_default_callback, nullptr); | ||
| } |
Member
Author
There was a problem hiding this comment.
@ngxson Wasn't sure what is the intent here of gating this with is_resume. I just moved the mtmd log initialization to the constructor server_context_impl(). Please confirm this is OK.
Contributor
There was a problem hiding this comment.
the reason why it's gated was because mtmd_helper_log_set is not thread-safe, so it should only be called once when the program starts.
although, there is another way, you can call mtmd_helper_log_set unconditionally in server_context_impl::init() function
github-actions
Bot
added
examples
server
ggml
Member
Author
|
@ggml-org/maintainers After this change the server logs will be quite reduced by default. You can easily go back to the old amount of logs if you are used to them by adding |
ServeurpersoCom
approved these changes
May 14, 2026
pwilkin
approved these changes
May 14, 2026
Member
pwilkin
left a comment
pwilkin
left a comment
There was a problem hiding this comment.
Good change, I like the added verbosity levels. Previously it was really hard to find a balance between standard mode that hid a lot of things and verbose mode that spammed tons of info on every token generated.
ngxson
reviewed
May 14, 2026
Comment on lines
+622
to
+625
| server_context_impl() { | ||
| mtmd_helper_log_set(common_log_default_callback, nullptr); | ||
| } | ||
|
|
ngxson
approved these changes
May 14, 2026
CISC
approved these changes
May 14, 2026
xxmustafacooTR
pushed a commit
to xxPlayground/llama-cpp-turboquant
that referenced
this pull request
May 14, 2026
* logs : reduce * args : fix envs * server : fix build * common : print verbosity level at start * server : clean-up logs * server : print prompt processing timings + sampling params * minor : whitespaces
dandm1
pushed a commit
to dandm1/llama.cpp
that referenced
this pull request
May 16, 2026
* logs : reduce * args : fix envs * server : fix build * common : print verbosity level at start * server : clean-up logs * server : print prompt processing timings + sampling params * minor : whitespaces
Bikkies
added a commit
to Bikkies/llama.cpp
that referenced
this pull request
May 17, 2026
- Opt-in flag that surfaces the per-device free-memory probe table (currently TRACE-only after ggml-org#23021) at INFO when set; default off.
rsenthilkumar6
pushed a commit
to rsenthilkumar6/llama.cpp
that referenced
this pull request
May 19, 2026
* logs : reduce * args : fix envs * server : fix build * common : print verbosity level at start * server : clean-up logs * server : print prompt processing timings + sampling params * minor : whitespaces
ArberSephirotheca
pushed a commit
to ArberSephirotheca/llama.cpp
that referenced
this pull request
May 19, 2026
* logs : reduce * args : fix envs * server : fix build * common : print verbosity level at start * server : clean-up logs * server : print prompt processing timings + sampling params * minor : whitespaces
baramofme
pushed a commit
to baramofme/llama-cpp-turboquant
that referenced
this pull request
May 23, 2026
* logs : reduce * args : fix envs * server : fix build * common : print verbosity level at start * server : clean-up logs * server : print prompt processing timings + sampling params * minor : whitespaces
winstonma
pushed a commit
to winstonma/llama.cpp
that referenced
this pull request
May 27, 2026
* logs : reduce * args : fix envs * server : fix build * common : print verbosity level at start * server : clean-up logs * server : print prompt processing timings + sampling params * minor : whitespaces
fewtarius
pushed a commit
to fewtarius/llama.cpp
that referenced
this pull request
May 30, 2026
* logs : reduce * args : fix envs * server : fix build * common : print verbosity level at start * server : clean-up logs * server : print prompt processing timings + sampling params * minor : whitespaces
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 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.
Overview
Reducing the amount of logs that we print by default. Feedback is welcome about what to remove further and what to keep.
Additional information
LOG_LEVEL_TRACE = 4LOG_LEVEL_DEBUGfrom 4 to 5INFOlogs coming fromlibllama,libmtmdandlibggml*toLOG_LEVEL_TRACElibcommonaccordinglyThe old level of logging can be enabled by adding
-lv 4to the CLI args.Requirements