Block a user
b741f9b20b
llm-inference-multimodel: repoint qwen shadow slot to Qwen2.5-14B-Instruct-1M (base Qwen disqualified, n_ctx_train=32768)
a3c1342837
llm-inference-multimodel: reset qwen shadow unit to disabled by default -- model disqualified (n_ctx_train=32768, not 64K+), leaving enabled would crash-loop on next playbook run
d4ff2681ac
llm-inference-multimodel: fix qwen unit -- llama.cpp requires --flash-attn <on|off|auto>, not bare flag
75cb93f25c
llm-inference-multimodel: enable Qwen2.5-14B shadow instance (port 8002) for shadow-test window
d10255297c
llm-inference-multimodel: add Qwen2.5-14B shadow instance (port 8002, gated off — VRAM co-residency not yet confirmed)
79edb8f4e1
llm-inference-multimodel: log Run 2 validation PASS (tool-calling + hallucination), preserve procedure doc
5dc76a8348
llm-inference-multimodel: fix tool-calling support (jinja template + gpu-layers=20 for VRAM fit)
a76ad3195c
llm-inference-multimodel: fix verify.yml losing Gemma-stop gate when run with --tags verify
73ef806dd6
llm-inference-multimodel: stop pre-existing Gemma service before Phase 4 starts new instances
aff792a061
feat(llm-inference): move astro-orbiter monitoring to GitOps (values.yaml + dashboards.yaml)