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.
## Summary
Replaces hand-applied `llm-serving-default-deny` NetworkPolicy with a git-managed, namespace-scoped policy that only allows traffic from the api-gateway.
**Issue:** #13
Co-authored-by: rock <[email protected]>
reasoning keeps its 2 GPUs untouched. verifier's freed GPU goes to a second ornith replica instead of a standalone qwen-only pod -- both replicas load ornith:35b + qwen2.5:3b-instruct, k8s Service load-balances across them, so 2 concurrent implementer-style calls get independent instances.
Frees verifier's GPU from an underused vLLM PRM deployment. qwen2.5:3b-instruct moves off ornith-predictor's shared pod onto its own dedicated GPU (grm.yaml), so verification/judge traffic stops contending with ornith:35b's agent traffic. /v1/qwen/chat/completions now points at grm-predictor; path unchanged.
rock
Story Crater Bot