Drittes Profil nach GNAI-009 3.4: Download 22,2 GiB SHA-256-verifiziert, S0-Bring-up 64k, S1 128k (n_ctx_slot=131072, VRAM 15,1/14,9 GiB), Health, Alias, Thinking- und Tool-Call-Tests bestanden, Prefill-Leiter 684/676/576/423 t/s (Unsloth-Niveau, Swift 1.0 deutlich darunter), Kontext-Negativtest sauber. Stabilitaetsstunde laeuft parallel; group_vars auf 128k zurueckgestellt. Swift 1.5 bleibt bis zur AB-Bewertung aktives Profil. Generated by Mistral Vibe. Co-Authored-By: Mistral Vibe <vibe@mistral.ai>
LLM serving stack
This directory will hold the executable infrastructure for the LLM serving
stack on ghostnet-ki: rootless llama.cpp with ROCm, separated into
Production and Testing environments.
It is created with the internal LLM vertical slice (roadmap milestone 2 in
GNAI-001). The planned
architecture, deployment and serving configuration are documented under
../../docs/platform/llm-server/ai/.