kdeps-recipes-llamacpp

id: llamacpp
name: llama.cpp server
description: Official llama.cpp server image (OpenAI-compatible /v1) for GGUF
version: 1.0.0

api:
  port: 8000
  base_path: /v1
  chat_path: /v1/chat/completions
  health:
    method: GET
    path: /v1/models
  auth:
    mode: none
    env: LLM_API_KEY

engine:
  kind: llamacpp
  base_image: "ghcr.io/ggerganov/llama.cpp:server"
  packages: []
  install: |
    true
  command:
    - sh
    - -c
    - exec /app/llama-server --host 0.0.0.0 --port 8000 -m "${LLM_MODEL:-/models/model.gguf}"
  env: {}
  internal_port: 8000
  openai_bridge: false

models:
  strategy: copy
  default: ""

resources:
  gpu: optional
  memory_hint: "8Gi"

capabilities:
  - chat