rockandpoimen
39f5fe3683
GPU rebalance (4× V100 32GB on worker-1): - reasoning: 2 GPU (unchanged, PP=2 for Qwen3-32B) - ornith: 2→1 GPU (scale to 1 replica, ornith:35b only) - comfyui: 0→1 GPU (new) - embeddings/reranker: 0 GPU (CPU, unchanged) qwen2.5:3b-instruct moved to CPU on talos-cp-2 (144GB RAM). Separate Ollama deployment + 5Gi PVC, pulls model on first start. Gateway config updated in homelab-frontend (separate commit). Co-authored-by: poimen <[email protected]>
100 lines
2.7 KiB
YAML
100 lines
2.7 KiB
YAML
apiVersion: serving.kserve.io/v1beta1
|
|
kind: InferenceService
|
|
metadata:
|
|
annotations:
|
|
serving.kserve.io/deploymentMode: RawDeployment
|
|
# The konghq.com/{connect,read,write}-timeout annotations that used to live
|
|
# here went with Kong (retired 2026-08-19). They existed because Kong read
|
|
# its upstream timeouts off the Kubernetes Service, and its 60s default cut
|
|
# off the first request after any pod restart — a restart flushes VRAM and
|
|
# reloading ornith:35b takes longer than that. OLLAMA_KEEP_ALIVE=-1 hid the
|
|
# problem in steady state.
|
|
#
|
|
# The equivalent budget now belongs to the Go gateway's per-route timeout
|
|
# config in rock/homelab-frontend, not to an annotation on this object.
|
|
labels:
|
|
app.kubernetes.io/name: llm-ornith
|
|
app.kubernetes.io/part-of: llm-serving
|
|
name: ornith
|
|
namespace: llm-serving
|
|
spec:
|
|
predictor:
|
|
containers:
|
|
- command:
|
|
- /bin/sh
|
|
- -c
|
|
- 'set -e
|
|
|
|
ollama serve &
|
|
|
|
SERVE_PID=$!
|
|
|
|
until ollama list >/dev/null 2>&1; do sleep 2; done
|
|
|
|
ollama pull ornith:35b
|
|
|
|
ollama run ornith:35b "ok" >/dev/null 2>&1 || true
|
|
|
|
wait $SERVE_PID
|
|
|
|
'
|
|
env:
|
|
- name: OLLAMA_HOST
|
|
value: 0.0.0.0:8080
|
|
- name: OLLAMA_MODELS
|
|
value: /mnt/models/ollama
|
|
- name: OLLAMA_CONTEXT_LENGTH
|
|
value: '32768'
|
|
- name: OLLAMA_KEEP_ALIVE
|
|
value: '-1'
|
|
- name: OLLAMA_NUM_PARALLEL
|
|
value: '1'
|
|
- name: OLLAMA_MAX_LOADED_MODELS
|
|
value: '1'
|
|
image: ollama/ollama:0.32.9@sha256:1685741456770df6e3cceb2a945a5f75e020f658d1701509668d6f4688f1dd3f
|
|
name: kserve-container
|
|
ports:
|
|
- containerPort: 8080
|
|
protocol: TCP
|
|
readinessProbe:
|
|
exec:
|
|
command:
|
|
- /bin/sh
|
|
- -c
|
|
- ollama ps 2>/dev/null | grep -q ornith
|
|
periodSeconds: 10
|
|
resources:
|
|
limits:
|
|
cpu: '16'
|
|
memory: 16Gi
|
|
nvidia.com/gpu: '1'
|
|
requests:
|
|
cpu: '8'
|
|
memory: 8Gi
|
|
nvidia.com/gpu: '1'
|
|
startupProbe:
|
|
exec:
|
|
command:
|
|
- /bin/sh
|
|
- -c
|
|
- ollama ps 2>/dev/null | grep -q ornith
|
|
failureThreshold: 120
|
|
periodSeconds: 15
|
|
volumeMounts:
|
|
- mountPath: /mnt/models
|
|
name: models
|
|
deploymentStrategy:
|
|
type: Recreate
|
|
# 1 replica -- ornith:35b only. qwen2.5:3b moved to CPU on cp-2.
|
|
# Frees 1 GPU for ComfyUI.
|
|
maxReplicas: 1
|
|
minReplicas: 1
|
|
nodeSelector:
|
|
kubernetes.io/hostname: worker-1
|
|
runtimeClassName: nvidia
|
|
volumes:
|
|
- name: models
|
|
persistentVolumeClaim:
|
|
claimName: llm-models
|
|
|