Commit Graph

4 Commits

Author SHA1 Message Date
unkinben e05f9bfd83 feat: increase litellm resources (#144)
finding litellm performance has dropped, crashed in multiple cases, and
then it had scaled to the maximum level using the majority of memory in
cluster.

- reduce the rate at which litellm autoscales
- increase the requests/limits to match usage

Reviewed-on: #144
2026-05-23 17:59:43 +10:00
unkinben 6138afb98b feat: add litellm-env configmap with STORE_MODEL_IN_DB=True (#97)
Reviewed-on: #97
2026-05-01 22:17:53 +10:00
unkinben 949ddb76e4 chore: litellm ooming (#95)
- update memory and cpu resources

Reviewed-on: #95
2026-05-01 21:54:00 +10:00
unkinben 5372914803 feat: add litellm to new aitooling ArgoCD project (#94)
Deploys LiteLLM proxy with CNPG PostgreSQL (3-instance HA), PgBouncer
pooler, and Redis cache. Introduces a dedicated aitooling AppProject and
ApplicationSet to keep AI tooling services separate from platform infra.

Reviewed-on: #94
2026-05-01 21:40:26 +10:00