tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : fix divide-by-zero in metrics reporting (#11915)

Browse Source
This commit is contained in:
Antoine Viallon
2025-02-17 11:25:12 +01:00
committed by GitHub
parent 2eea03d86a
commit c4d29baf32
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/server.cpp
View File

@ -3656,7 +3656,7 @@ int main(int argc, char ** argv) {
}, {
{"name", "n_busy_slots_per_decode"},
{"help", "Average number of busy slots per llama_decode() call"},
{"value", (float) res_metrics->n_busy_slots_total / (float) res_metrics->n_decode_total}
{"value", (float) res_metrics->n_busy_slots_total / std::max((float) res_metrics->n_decode_total, 1.f)}
}}},
{"gauge", {{
{"name", "prompt_tokens_seconds"},