rock 7bdc8b2de2 fix(llm-serving): set runtimeClassName nvidia on the candle deployment ...

Without it the container runs under runc, libcuda.so is never injected and
candle-vllm panics in cudarc at startup. The pod reached Running but crashed
on every restart.

Verified live: pod Ready, coder-predictor endpoints populated, /v1/models
reports coder-14b-fp16 and a completion returns OK.

2026-11-05 09:22:48 +08:00

..

agent-pod

feat: cut api.riotpiao.com over to the Go gateway and retire Kong

2026-08-19 22:51:53 -07:00

api

feat: point api.riotpiao.com at the gateway ahead of Kong removal

2026-08-19 23:34:33 -07:00

cloudflared

revert(cloudflared): do not publish the kube-apiserver at k8s.riotpiao.com (#105)

2026-11-03 22:04:28 +00:00

gotify

fix(gotify): run gotify-db with 2 instances, not 3

2026-11-04 05:24:09 +08:00

immich

fix(cnpg): scale paperless-db, immich-db, gotify-db to 3 instances (#30)

2026-09-10 22:56:41 +00:00

key-rotation-controller

chore(comfyui): retire the app for good

2026-11-04 03:44:07 +08:00

llm-serving

fix(llm-serving): set runtimeClassName nvidia on the candle deployment

2026-11-05 09:22:48 +08:00

llm-token-vendor

feat(paperless-ai): mint the LLM token with a machine key, not an init container

2026-10-27 23:48:45 -07:00

messaging

chore(authentik): finish the retirement in Terraform and messaging

2026-10-27 13:31:02 -07:00

paperless

fix(paperless-ai): ask for no project audience, so aud names the caller

2026-10-28 01:34:23 -07:00

poimen-frontend

feat(poimen): publish the memory API at api-poimen.riotpiao.com

2026-11-04 04:52:11 +08:00

portainer

fix(portainer): pin to az-b (talos-cp-2), the real Longhorn storage node

2026-08-18 15:08:04 -07:00

temporal

Add Temporal worker for production task queue

2026-08-21 16:44:59 -07:00