phase 17: switch to qwen3.5:9b-fast (32k context), add queue management scripts

This commit is contained in:
Celes Renata
2026-04-12 10:19:28 -07:00
parent 1993bfdf3e
commit 7ee1d0f050
3 changed files with 39 additions and 1 deletions
+1 -1
View File
@@ -159,7 +159,7 @@ config:
MINIO_ENDPOINT: "minio.minio-service.svc.cluster.local:80"
MINIO_SECURE: "false"
OLLAMA_BASE_URL: "http://ollama.ollama-service.svc.cluster.local:11434"
OLLAMA_MODEL: "qwen3.5:9b"
OLLAMA_MODEL: "qwen3.5:9b-fast"
OLLAMA_TIMEOUT: "120"
OLLAMA_MAX_RETRIES: "2"
OLLAMA_RETRY_BASE_DELAY: "1.0"