upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-06 10:00:48 -05:00
Code Issues Packages Projects Releases Wiki Activity

server: Adding spec-decode counters to /metrics endpoint (#26389)

Browse Source 
* * server: add spec-decode counters to /metrics endpoint

* server: fixed review comments and now aligned param names exactly with vLLM.
This commit is contained in:
Bhavik Sharda
2026-08-05 16:06:01 +05:30
committed by GitHub
parent 020760adfc
commit a035a88878
4 changed files with 58 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
tools/server/server-task.cpp
View File

@@ -1560,6 +1560,11 @@ json server_task_result_metrics::to_json() {
{ "n_decode_total", n_decode_total },
{ "n_busy_slots_total", n_busy_slots_total },
{ "n_draft_tokens_total", n_draft_tokens_total },
{ "n_draft_accepted_total", n_draft_accepted_total },
{ "n_draft_verif_steps_total", n_draft_verif_steps_total },
{ "n_accepted_per_pos_total", n_accepted_per_pos_total },
{ "slots", slots_data },
};
}