upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-30 09:57:38 -05:00
Code Issues Packages Projects Releases Wiki Activity

more accurate batch metrics tracking

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-08-12 13:25:43 +02:00
parent 20ce126733
commit 372ea5734d
3 changed files with 90 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-task.cpp
+4 -4
View File
@@ -1518,16 +1518,16 @@ json server_task_result_metrics::to_json() {
{ "t_start", t_start },
{ "n_prompt_tokens_processed_total", prompt.count },
{ "t_tokens_generation_total", predict.time },
{ "t_tokens_generation_total", predict.time / 1e3 },
{ "n_tokens_predicted_total", predict.count },
{ "t_prompt_processing_total", prompt.time },
{ "t_prompt_processing_total", prompt.time / 1e3 },
{ "n_tokens_max", n_tokens_max },
{ "n_prompt_tokens_processed", prompt_bucket.count },
{ "t_prompt_processing", prompt_bucket.time },
{ "t_prompt_processing", prompt_bucket.time / 1e3 },
{ "n_tokens_predicted", predict_bucket.count },
{ "t_tokens_generation", predict_bucket.time },
{ "t_tokens_generation", predict_bucket.time / 1e3 },
{ "n_decode_total", n_decode },
{ "n_busy_slots_total", n_busy_slots },