Xuan-Son Nguyen
decaf508bb
server: refactor + correctness fixes for metrics (#26920)
* server: refactor metrics
* move most fields to server_slot_stats
* cont
* rm result_timings
* tie stats to batch
* cont
* nits: move place in code
* exclude first generated token
* more accurate batch metrics tracking
* n_predict --> n_gen
* metrics_on_prediction
* metrics_flush_idle
* metrics: seperate cache/processed prompt tokens
* refactor server_task_result_metrics
* add test
* nits
* fix flush before reset()
* cont
* rm dead code
* nits
2026-08-13 10:02:01 +02:00
..
2026-05-22 11:46:26 +03:00
2026-08-11 09:20:46 +03:00
2026-08-11 09:20:46 +03:00
2026-08-12 14:15:03 +02:00
2026-06-18 16:46:17 +02:00
2026-05-22 11:46:26 +03:00
2026-08-12 14:15:03 +02:00
2026-08-11 11:18:19 -04:00
2026-08-11 09:20:46 +03:00
2026-08-12 14:15:03 +02:00
2026-08-01 00:13:07 -05:00
2026-05-28 10:34:58 +03:00
2026-08-12 14:15:03 +02:00
2026-04-17 11:11:46 +03:00
2026-06-27 10:31:29 +03:00
2026-08-13 10:02:01 +02:00
2026-07-15 18:41:51 +02:00
2026-08-11 14:18:30 +02:00
2026-08-13 08:21:15 +02:00
2026-06-04 13:13:19 +03:00