homelab

riotpiao-poimen/homelab

Fork 0

Author	SHA1	Message	Date
rock	44fbf071e1	chore(llm-serving): park clef-serve to free a V100 for candle-vllm candle-vllm cannot start. worker-1 has four V100-32GB and all four are allocated: coder 2, reasoning 1, clef-serve 1. Free is 0, so a new GPU pod sits Pending no matter what it is. This pod is the only GPU consumer in the namespace that is not vLLM, so it is the only card that can be released without breaking the instruction to keep vLLM healthy until candle-vllm answers. Ingest keeps running on reasoning-predictor, and pi keeps its coder model on coder-predictor. It was not serving anything. At park time its last 30 log lines were 30 of 30 kubelet /health probes, with no inference request since it started on 2026-10-30T06:23:40Z. Nothing in git selects this Service. It held a card for a day to answer liveness probes, which is the same shape as the comfyui retirement. Reversible: set replicas back to 1. It should return once the rollout settles, because 30B-A3B takes 1 card and Coder-Next TP=2 takes 2, which leaves card 4 for this workload. Not applied. ArgoCD runs selfHeal for llm-serving, so a live scale to 0 is reverted within minutes; this needs the merge to stick.	2026-10-31 19:40:27 -07:00

Author

SHA1

Message

Date

rock

44fbf071e1

chore(llm-serving): park clef-serve to free a V100 for candle-vllm

candle-vllm cannot start. worker-1 has four V100-32GB and all four are
allocated: coder 2, reasoning 1, clef-serve 1. Free is 0, so a new GPU pod
sits Pending no matter what it is.

This pod is the only GPU consumer in the namespace that is not vLLM, so it is
the only card that can be released without breaking the instruction to keep
vLLM healthy until candle-vllm answers. Ingest keeps running on
reasoning-predictor, and pi keeps its coder model on coder-predictor.

It was not serving anything. At park time its last 30 log lines were 30 of 30
kubelet /health probes, with no inference request since it started on
2026-10-30T06:23:40Z. Nothing in git selects this Service. It held a card for a
day to answer liveness probes, which is the same shape as the comfyui
retirement.

Reversible: set replicas back to 1. It should return once the rollout settles,
because 30B-A3B takes 1 card and Coder-Next TP=2 takes 2, which leaves card 4
for this workload.

Not applied. ArgoCD runs selfHeal for llm-serving, so a live scale to 0 is
reverted within minutes; this needs the merge to stick.

2026-10-31 19:40:27 -07:00

Compare commits

Diff Content Not Available