From 75bd4c3679331b484388d398e9eb94f199d5e5b7 Mon Sep 17 00:00:00 2001 From: Vuong Hoang Date: Fri, 19 Jun 2026 11:56:20 -0700 Subject: [PATCH] remove gen-nt / gen-reasoning-nt litellm records (operator) Source + deployed config cleaned without bouncing the gateway. NOTE: these were config-loaded models, which the /model/delete API can't remove (DB-only -> 'not found in db'), so the LIVE gateway still serves them until its next restart, at which point the cleaned config drops them. No bounce performed. --- stacks/litellm/conf/config.yaml | 49 --------------------------------- 1 file changed, 49 deletions(-) diff --git a/stacks/litellm/conf/config.yaml b/stacks/litellm/conf/config.yaml index d5c3f35..6ab7296 100644 --- a/stacks/litellm/conf/config.yaml +++ b/stacks/litellm/conf/config.yaml @@ -134,55 +134,6 @@ model_list: enable_thinking: true model_info: mode: chat - # --- gen-nt / gen-reasoning-nt: same Qwopus `gen` model, but with a dummy `noop` - # tool + tool_choice:"none" baked into the record so a NON-EMPTY tools array - # always reaches vLLM (which 400s on an empty `tools:[]`). For consumers where - # the global strip_empty_tools hook isn't the right fix — i.e. they need a valid - # tools structure PRESENT rather than stripped. tool_choice:none disables actual - # calling, so the noop is never invoked. api_base = the real LAN endpoint (the - # operator's `http://vllm:8000` template wouldn't resolve from ana-docker). --- - - model_name: gen-nt - litellm_params: - model: hosted_vllm/qwen3.5-122-a10b - api_base: http://10.250.50.54:8013/v1 - api_key: os.environ/VLLM_API_KEY - extra_body: - chat_template_kwargs: - enable_thinking: false - tools: - - type: function - function: - name: noop - description: "No-op tool. Do not call this tool; it exists only for compatibility." - parameters: - type: object - properties: {} - required: [] - additionalProperties: false - tool_choice: "none" - model_info: - mode: chat - - model_name: gen-reasoning-nt - litellm_params: - model: hosted_vllm/qwen3.5-122-a10b - api_base: http://10.250.50.54:8013/v1 - api_key: os.environ/VLLM_API_KEY - extra_body: - chat_template_kwargs: - enable_thinking: true - tools: - - type: function - function: - name: noop - description: "No-op tool. Do not call this tool; it exists only for compatibility." - parameters: - type: object - properties: {} - required: [] - additionalProperties: false - tool_choice: "none" - model_info: - mode: chat # --- Selene 1 Mini 8B (AtlaAI judge, FP8) — restored on GPU1 after the # llama-swap teardown (was the Q6_K GGUF in the swap zoo). vLLM dynamic fp8,