feat(llm-serving): retire verifier-predictor, add grm (qwen2.5:3b)

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.
2026-08-18 18:18:31 -07:00
parent e6ada95b39
commit 50d00ae350
5 changed files with 115 additions and 126 deletions
@@ -11,9 +11,9 @@ kind: Kustomization
 # in tens of seconds, not a rolling update.
 resources:
  - embeddings.yaml
+  - grm.yaml
  - ornith.yaml
  - reasoning.yaml
  - reranker.yaml
-  - verifier.yaml
 # No namespace transformer: every file sets its own, and the transformer would
 # rewrite metadata.namespace on anything cross-namespace added later.