Skip to content

fix: route llama.cpp log fallback to stderr instead of stdout #609

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
andreinknv wants to merge 1 commit into
base: master
Choose a base branch
from
Open

fix: route llama.cpp log fallback to stderr instead of stdout #609

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 9 additions & 14 deletions llama/addon/globals/addonLog.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,13 +38,11 @@ void addonCallJsLogCallback(
}

if (!called && data != nullptr) {
if (data->logLevelNumber == 2) {
fputs(data->stringStream->str().c_str(), stderr);
fflush(stderr);
} else {
fputs(data->stringStream->str().c_str(), stdout);
fflush(stdout);
}
// llama.cpp diagnostics go to stderr regardless of level —
// stdout is the host process's data / JSON-RPC channel and
// must not be polluted with library log lines.
fputs(data->stringStream->str().c_str(), stderr);
fflush(stderr);
}

if (data != nullptr) {
Expand Down Expand Up @@ -83,13 +81,10 @@ void addonLlamaCppLogCallback(ggml_log_level level, const char* text, void* user
}

if (text != nullptr) {
if (level == 2) {
fputs(text, stderr);
fflush(stderr);
} else {
fputs(text, stdout);
fflush(stdout);
}
// All llama.cpp log output goes to stderr — see the note in
// addonCallJsLogCallback; stdout is the host's data channel.
fputs(text, stderr);
fflush(stderr);
}
}

Expand Down