8 Commits

Author SHA1 Message Date
579185654b polish 2026-05-19 21:21:42 +02:00
b379faebdb change scheduling strategy to hibrid priority queue with aging 2026-05-19 20:57:38 +02:00
7cf16dcace improve cache 2026-05-18 01:02:57 +02:00
bcebaf0e93 improve monitoring 2026-05-18 00:25:10 +02:00
47d4b4e4fc scheduler : improve backend usage 2026-05-17 23:38:43 +02:00
1dbb1c7f6f add per model limits 2026-05-17 23:07:21 +02:00
d826b038ab fixes 2026-05-17 22:15:13 +02:00
7344aa4ef4 first commit 2026-05-17 09:54:18 +02:00