From 564f5ae4f651f288a5092e8b441e9df32521fe75 Mon Sep 17 00:00:00 2001 From: Vuong Hoang Date: Fri, 21 Aug 2026 07:50:10 -0700 Subject: [PATCH] chore(litellm): rename mog-sec aliases to sec / sec-reasoning Operator's call: the pen-test seat is reached as `sec` (non-thinking) and `sec-reasoning` (thinking). Backend and served-model-names (mog-sec-27b[-thinking] on :8019) are unchanged; only the gateway alias name changes. Old mog-sec / mog-sec-reasoning now 404. --- stacks/litellm/conf/config.yaml | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/stacks/litellm/conf/config.yaml b/stacks/litellm/conf/config.yaml index ed9e5a7..6b4053f 100644 --- a/stacks/litellm/conf/config.yaml +++ b/stacks/litellm/conf/config.yaml @@ -267,14 +267,14 @@ model_list: # down, weights intact) if it is ever wanted back. Not repointed to mog-sec # -- a security model is not an RP-reasoning model (no false aliases). --- - # --- mog-sec -> M.O.G.-SEC-27B pen-test seat (ana-ml2 GPU1 :8019, in the retired + # --- sec (was mog-sec, renamed 2026-08-21) -> M.O.G.-SEC-27B pen-test seat (ana-ml2 GPU1 :8019, in the retired # fable slot). Blackfrost-Research/M.O.G.-SEC-27B-1M-CTX, stock-Qwen3.8-27B # base, quantized in-house to mixed NVFP4+FP8 with MTP + vision preserved. # Served at native 262K (NOT the card's 1M -- that needs YaRN + SGLang/DFlash2, # not our vLLM path). presence_penalty deliberately 0.0, NOT the fleet's 1.5: # this is a code/security tool and the anti-repetition penalty fights code # structure (and upstream warns it can cause language mixing). Non-thinking. --- - - model_name: mog-sec + - model_name: sec litellm_params: model: hosted_vllm/mog-sec-27b api_base: http://10.250.50.54:8019/v1 @@ -290,10 +290,10 @@ model_list: enable_thinking: false model_info: mode: chat - # mog-sec-reasoning -> the SAME seat, thinking ON. Distinct served-name so a + # sec-reasoning -> the SAME seat, thinking ON. Distinct served-name so a # thinking-off request can't mutate this deployment's enable_thinking (the # shared-config clobber). Canonical Qwen3.8 thinking samplers (temp 1.0/top_p 0.95). - - model_name: mog-sec-reasoning + - model_name: sec-reasoning litellm_params: model: hosted_vllm/mog-sec-27b-thinking api_base: http://10.250.50.54:8019/v1