33 lines
1.2 KiB
YAML
33 lines
1.2 KiB
YAML
|
# Shared HuggingFace cache for all three engines.
|
||
|
|
#
|
||
|
|
# ReadWriteOnce is correct here despite six pods mounting it: RWO means "one
|
||
|
|
# NODE", and every pod in this app is pinned to worker-1 via nodeSelector, so
|
||
|
|
# they share the volume legally. If a pod is ever allowed onto another node,
|
||
|
|
# this must become RWX first.
|
||
|
|
#
|
||
|
|
# StorageClass is longhorn-llm-local (1 replica, strict-local, disk tag `llm`)
|
||
|
|
# — NOT the default 3-replica class, which could not place this volume at all:
|
||
|
|
# every control-plane disk was already at its over-provisioning ceiling.
|
||
|
|
#
|
||
|
|
# Sizing (measured, not estimated):
|
||
|
|
# reasoning GPTQ INT4 19.3 GB
|
||
|
|
# ornith:35b q4 (ollama) 21.0 GB
|
||
|
|
# verifier Qwen2.5-Math-PRM-7B fp16 15.3 GB
|
||
|
|
# nomic-embed-text-v2-moe (CPU) 1.9 GB
|
||
|
|
# bge-reranker-base (CPU) 1.1 GB
|
||
|
|
# ------------------------------------------
|
||
|
|
# total ~58.6 GB (+ HF temp during pulls)
|
||
|
|
# The two reasoning replicas share ONE on-disk copy; they differ only in which
|
||
|
|
# GPU they load it onto.
|
||
|
|
apiVersion: v1
|
||
|
|
kind: PersistentVolumeClaim
|
||
|
|
metadata:
|
||
|
|
name: llm-models
|
||
|
|
spec:
|
||
|
|
accessModes:
|
||
|
|
- ReadWriteOnce
|
||
|
|
storageClassName: longhorn-llm-local
|
||
|
|
resources:
|
||
|
|
requests:
|
||
|
|
storage: 120Gi
|