happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

server : log levels

This commit is contained in:
Sascha Rogmann 2026-02-10 23:51:27 +01:00
parent e002b095e5
commit 01763e800d
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
tools/server/server-context.cpp
View File

@ -2149,7 +2149,7 @@ private:
slot.prompt.tokens.push_back(slot.sampled);
if (slot.task->params.speculative.n_min > (int) draft.size()) {
SLT_INF(slot, "ignoring small draft: %d < %d\n", (int) draft.size(), slot.task->params.speculative.n_min);
SLT_DBG(slot, "ignoring small draft: %d < %d\n", (int) draft.size(), slot.task->params.speculative.n_min);
// fallback to normal decoding
slot.i_batch = slot.i_batch_dft[0];
slot.drafted.clear();
@ -2682,10 +2682,10 @@ private:
// do not checkpoint after mtmd chunks
do_checkpoint = do_checkpoint && !has_mtmd;
SLT_INF(slot, "main/do_checkpoint = %s, pos_min = %d, pos_max = %d\n", do_checkpoint ? "yes" : "no", pos_min, pos_max);
// no need to create checkpoints that are too close together
do_checkpoint = do_checkpoint && (slot.prompt.checkpoints.empty() || slot.prompt.n_tokens() - n_tokens_cur > slot.prompt.checkpoints.back().n_tokens + 64);
SLT_DBG(slot, "main/do_checkpoint = %s, pos_min = %d, pos_max = %d\n", do_checkpoint ? "yes" : "no", pos_min, pos_max);
// note: we create the checkpoint before calling llama_decode(), so the current batch is not
// yet processed and therefore it is not part of the checkpoint.