rock
9aec1b3e30
The gateway already dispatches /v1/systemone and its config already names clef-flash-predictor, but this directory is an explicit allowlist and clef-flash.yaml was not on it, so the model was silently dropped: no error, no drift, just no predictor. clef-flash is a decision model, not a chat model. It reads a state plus a schema of typed questions and returns one probability per allowed option in a single prefill pass, with no decode step. It needs SGLang rather than vLLM because it loads separate joint_schema_head weights on top of the Qwen3.5-9B backbone and it implements the /v1/systemone route. worker-1 has four GPUs: reasoning holds two, ornith holds one, so one is free and this fits without retiring ornith first.
22 lines
948 B
YAML
22 lines
948 B
YAML
apiVersion: kustomize.config.k8s.io/v1beta1
|
|
kind: Kustomization
|
|
# Explicit allowlist, matching k8s/apps/api. Anything added to this directory
|
|
# and not listed here is silently dropped — no error, no drift shown.
|
|
#
|
|
# These five were adopted from live state on 2026-08-15; they had been applied
|
|
# by hand and carried no ArgoCD ownership. Each was exported and verified with
|
|
# `kubectl diff -f <file>` returning empty before the Application below was
|
|
# created, so the first sync was a no-op rather than a redeploy. Re-verify that
|
|
# way after any edit here: a GPU predictor restart is a weights reload measured
|
|
# in tens of seconds, not a rolling update.
|
|
resources:
|
|
- clef-flash.yaml
|
|
- embeddings.yaml
|
|
- ornith.yaml
|
|
- reasoning.yaml
|
|
- reranker.yaml
|
|
- qwen-cpu.yaml
|
|
- networkpolicy.yaml
|
|
# No namespace transformer: every file sets its own, and the transformer would
|
|
# rewrite metadata.namespace on anything cross-namespace added later.
|