Skip to content

llama-server : Reduce log level of a debug message leaking prompt contents #16727

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

Closed
wants to merge 1 commit into from
+5 −5
Closed

llama-server : Reduce log level of a debug message leaking prompt contents #16727

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
10 changes: 5 additions & 5 deletions tools/server/server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3818,7 +3818,7 @@ struct server_context {

// when the prompt prefix does not match, print the tokens around the mismatch
// this is useful for debugging prompt caching
{
if (GGML_LOG_LEVEL_DEBUG <= common_log_verbosity_thold) {
const int np0 = std::max<int>(slot.n_past - 4, 0);
const int np1 = std::min<int>(slot.n_past + 6, std::min(slot.prompt.tokens.size(), slot.task->tokens.size()));

Expand Down Expand Up @@ -3852,11 +3852,11 @@ struct server_context {
}
}

SLT_WRN(slot, "%s\n", ss0.str().c_str());
SLT_WRN(slot, "%s\n", ss1.str().c_str());
SLT_DBG(slot, "%s\n", ss0.str().c_str());
SLT_DBG(slot, "%s\n", ss1.str().c_str());

SLT_WRN(slot, "%s\n", st0.str().c_str());
SLT_WRN(slot, "%s\n", st1.str().c_str());
SLT_DBG(slot, "%s\n", st0.str().c_str());
SLT_DBG(slot, "%s\n", st1.str().c_str());
}

if (pos_min > pos_min_thold) {
Expand Down
Loading