llama.cpp
server: refactor + correctness fixes for metrics
#26920
Merged

server: refactor + correctness fixes for metrics #26920

ServeurpersoCom merged 20 commits into master from xsn/refactor_server_metrics
ngxson
ngxson server: refactor metrics
14bb119b
ngxson ngxson changed the title server: refactor metrics server: refactor + correctness fixes for metrics 51 days ago
github-actions github-actions added server
ngxson move most fields to server_slot_stats
22170592
ngxson cont
b16f898b
ngxson rm result_timings
75d2de4b
ngxson tie stats to batch
7d59fa38
ngxson cont
2581e568
ngxson nits: move place in code
a2fd44e3
ngxson exclude first generated token
20ce1267
ngxson more accurate batch metrics tracking
372ea573
ngxson n_predict --> n_gen
509866bc
ngxson metrics_on_prediction
6849901f
ngxson metrics_flush_idle
a55abe44
ngxson metrics: seperate cache/processed prompt tokens
e0f113de
ngxson refactor server_task_result_metrics
9c57fd78
ngxson add test
9138c133
ngxson nits
c53ad201
ngxson fix flush before reset()
a46d5259
ngxson cont
ef51649a
ngxson rm dead code
27615964
ngxson nits
b7d9c4cc
ngxson ngxson marked this pull request as ready for review 50 days ago
ngxson ngxson requested a review 50 days ago
ngxson
ngxson commented on 2026-08-12
ngxson
ServeurpersoCom
ServeurpersoCom approved these changes on 2026-08-13
ggerganov
ggerganov approved these changes on 2026-08-13
ServeurpersoCom ServeurpersoCom merged decaf508 into master 50 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone