apiVersion: v1
kind: ConfigMap
metadata:
  name: llamacpp-config
data:
  LLAMA_CACHE: /models
  LLAMA_ARG_HOST: 0.0.0.0
  LLAMA_ARG_PORT: "8080"
  # The model is chosen here: <hf-user>/<repo>:<quant>. It is downloaded into
  # /models on first start; changing it restarts the pod (reloader).
  LLAMA_ARG_HF_REPO: "unsloth/Qwen3.8-27B-GGUF:UD-Q6_K"
  LLAMA_ARG_CTX_SIZE: "131072"
  LLAMA_ARG_N_GPU_LAYERS: all
  LLAMA_ARG_FLASH_ATTN: "on"
  LLAMA_ARG_FIT: "on"
  # Strix Halo: mmap-ed weights hang or corrupt on ROCm; read them directly.
  LLAMA_ARG_LOAD_MODE: dio