From 207798de660d64722c0bb64c2802fb4422f01fb3 Mon Sep 17 00:00:00 2001 From: Vuong Hoang Date: Mon, 14 Sep 2026 07:49:40 -0700 Subject: [PATCH] feat(litellm): promote cyberprev into the sec / sec-reasoning seats; retire mog-sec Operator instruction: take down the existing sec seat (mog-sec) and promote hotdogs (cyberprev) into the sec and sec-reasoning gateway seats. - mog-sec container (vllm-mog-sec, :8019, fv-ml1 GPU0) taken down; ~48 GB freed on GPU0 (cyberprev, already co-resident there, is now the sole GPU0 chat seat). - Gateway sec -> hosted_vllm/cyberprev-27b @ :8025; sec-reasoning -> hosted_vllm/cyberprev-27b-thinking @ :8025. sec/sec-reasoning are ROLE aliases, so this is a promotion, not silent substitution (samplers were already identical between the sec blocks and cyberprev, so only model+api_base changed). - Removed the standalone cyberprev-27b / cyberprev-reasoning gateway aliases added in the prior commit -- now redundant with sec/sec-reasoning, and the fleet convention is a role alias on the gateway with the model's served-name only at the vLLM layer (as mog-sec had). cyberprev's vLLM served-names are unchanged. - Verified e2e through the gateway: sec answers (nmap -sV version detection), sec-reasoning answers with a thinking split (127 reasoning tokens); retired mog-sec-27b now 400s. Note: mog-sec was the fleet's only offense+defense/blue-team seat; the sec role is now offense-only (cyberprev tool-calling). Operator-directed after reviewing the capability comparison. mog-sec stack files retained for a future restore. --- stacks/litellm/conf/config.yaml | 46 +++------------------------------ 1 file changed, 4 insertions(+), 42 deletions(-) diff --git a/stacks/litellm/conf/config.yaml b/stacks/litellm/conf/config.yaml index eb8fae9..0552011 100644 --- a/stacks/litellm/conf/config.yaml +++ b/stacks/litellm/conf/config.yaml @@ -376,8 +376,8 @@ model_list: # structure (and upstream warns it can cause language mixing). Non-thinking. --- - model_name: sec litellm_params: - model: hosted_vllm/mog-sec-27b - api_base: http://10.251.50.54:8019/v1 + model: hosted_vllm/cyberprev-27b + api_base: http://10.251.50.54:8025/v1 api_key: os.environ/VLLM_API_KEY temperature: 0.7 top_p: 0.8 @@ -395,8 +395,8 @@ model_list: # shared-config clobber). Canonical Qwen3.8 thinking samplers (temp 1.0/top_p 0.95). - model_name: sec-reasoning litellm_params: - model: hosted_vllm/mog-sec-27b-thinking - api_base: http://10.251.50.54:8019/v1 + model: hosted_vllm/cyberprev-27b-thinking + api_base: http://10.251.50.54:8025/v1 api_key: os.environ/VLLM_API_KEY temperature: 1.0 top_p: 0.95 @@ -970,44 +970,6 @@ model_list: mode: chat # cyberprev-27b -> hotdogs/Qwen3.8-27B-abliterated-cyber-preview (:8025, fv-ml1 GPU0). - # Cyber offensive-security tool-calling SFT (LoRA finetune on an abliterated base), in-house - # mixed NVFP4 quant, dflash k=7. Replaced the retired sentinel-r3 seat 2026-09-14. - # Sampler mirrors sec/sec-reasoning so an A/B isolates weights, not sampling. The retired - # sentinel-r3 aliases were DELETED, not repointed — cyberprev weights under sentinel's name - # would be silent substitution. - - model_name: cyberprev-27b - litellm_params: - model: hosted_vllm/cyberprev-27b - api_base: http://10.251.50.54:8025/v1 - api_key: os.environ/VLLM_API_KEY - temperature: 0.7 - top_p: 0.8 - presence_penalty: 0.0 - extra_body: - top_k: 20 - min_p: 0.0 - repetition_penalty: 1.0 - chat_template_kwargs: - enable_thinking: false - model_info: - mode: chat - - model_name: cyberprev-reasoning - litellm_params: - model: hosted_vllm/cyberprev-27b-thinking - api_base: http://10.251.50.54:8025/v1 - api_key: os.environ/VLLM_API_KEY - temperature: 1.0 - top_p: 0.95 - presence_penalty: 0.0 - extra_body: - top_k: 20 - min_p: 0.0 - repetition_penalty: 1.0 - chat_template_kwargs: - enable_thinking: true - model_info: - mode: chat - general_settings: master_key: os.environ/LITELLM_MASTER_KEY database_url: os.environ/DATABASE_URL