CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-05 09:36:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : don't print user inputs to console (#16871)

Browse Source
This commit is contained in:
Georgi Gerganov
2025-10-31 10:54:19 +02:00
committed by GitHub
parent 0f715b4e75
commit c22473b580
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/server/server.cpp
View File

@@ -3796,7 +3796,7 @@ struct server_context {
// when the prompt prefix does not match, print the tokens around the mismatch // when the prompt prefix does not match, print the tokens around the mismatch
// this is useful for debugging prompt caching // this is useful for debugging prompt caching
{ if (slots_debug) {
const int np0 = std::max<int>(n_past - 4, 0); const int np0 = std::max<int>(n_past - 4, 0);
const int np1 = std::min<int>(n_past + 6, std::min(slot.prompt.tokens.size(), slot.task->tokens.size())); const int np1 = std::min<int>(n_past + 6, std::min(slot.prompt.tokens.size(), slot.task->tokens.size()));