Commit Graph

19 Commits

Author SHA1 Message Date
platform-engineer
9c134d5dd0 fix(litellm): add memory and CPU resource limits to prevent OOMKilled
Litellm pod was being killed by the kernel OOM killer (7 restarts, last
termination reason: OOMKilled). Added explicit resource requests (512Mi/250m)
and limits (2Gi/1000m) to ensure the container gets bounded memory.
2026-07-21 21:59:15 +00:00
Roger Oriol
279cc1f235 configure litellm models 2026-07-14 21:45:18 +02:00
Roger Oriol
cf6e2784fe configure litellm models 2026-07-14 21:36:38 +02:00
Roger Oriol
9fd7d02c7c loki + promtail new monitoring services 2026-07-05 17:32:15 +02:00
Roger Oriol
1145214e24 fix hermes qwen model 2026-06-29 00:21:57 +02:00
Roger Oriol
6e02d9a885 new platform engineer agent 2026-06-27 00:09:39 +02:00
Roger Oriol
153cf16194 refactor ingresses 2026-06-23 00:26:29 +02:00
Roger Oriol
97172eebda configure litellm phoenix integration 2026-01-27 23:03:42 +01:00
Roger Oriol
f2a7a618ee set litellm verbose flag 2026-01-24 17:55:12 +01:00
Roger Oriol
40d12f307d set litellm verbose flag 2026-01-24 17:34:48 +01:00
Roger Oriol
2b8aa4df87 create litellm config file 2026-01-24 17:27:09 +01:00
Roger Oriol
88c4eca28d create litellm config file 2026-01-24 17:09:37 +01:00
Roger Oriol
0b006d047e create litellm config file 2026-01-24 16:59:57 +01:00
Roger Oriol
dede760adf create litellm config file 2026-01-24 16:50:24 +01:00
Roger Oriol
056a69ac51 create litellm config file 2026-01-24 16:41:24 +01:00
Roger Oriol
f6963f7501 change litellm image to main-latest 2026-01-24 15:59:09 +01:00
Roger Oriol
9a4a6c1485 add STORE_MODEL_IN_DB env var in litellm 2026-01-24 15:27:33 +01:00
Roger Oriol
d5d0958502 init cluster 2025-11-02 18:13:46 +01:00
Roger Oriol
915d40cdce initialize repository with glance, litellm, openwebui, nas and pihole services 2025-08-01 11:11:46 +02:00