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
..
2026-06-19 22:12:46 +02:00
2026-06-21 13:03:14 +02:00
2026-07-12 17:43:51 +02:00
2026-05-08 15:23:04 +02:00
2026-07-07 16:13:03 +02:00
2026-07-25 20:53:08 +02:00
2025-10-28 20:19:44 +02:00
2026-03-13 20:53:42 +02:00
2026-04-08 17:12:15 +02:00
2025-11-02 18:14:04 +02:00
2026-04-24 09:28:44 +03:00
2025-08-19 16:46:37 +03:00
2026-07-26 01:08:49 +02:00
2026-08-13 10:02:01 +02:00
2026-08-06 15:07:22 +02:00
2025-10-11 16:39:04 +03:00
2026-08-07 21:38:32 +03:00
2026-07-14 17:23:44 +02:00
2025-12-21 02:24:42 +01:00
2026-08-12 12:20:28 +02:00
2026-08-12 08:08:19 +03:00
2026-07-27 07:34:47 +02:00
2026-03-12 13:41:01 +01:00
2025-08-19 16:46:37 +03:00
2026-05-04 13:18:11 +02:00
2026-08-10 13:31:09 +02:00
2026-06-06 11:06:51 +02:00