# llama-swap stack tunables. Copy to `.env` on ana-docker before deploying.
#
#   cp .env.example .env
#   # edit if needed
#   docker compose up -d

# Image tag. `cuda` is the CUDA-enabled build; pin to a specific release
# (e.g. `cuda-v0.0.6`) for reproducibility once upstream tags stabilize.
LLAMA_SWAP_VERSION=cuda

# Host port for the OpenAI-compatible API (container listens on 8080)
LLAMA_SWAP_PORT=9292

# Host paths
# --- Legacy GGUF models referenced by config.yaml as `-m /models/<file>`
MODELS_DIR=/tank/aimodels/llm
# --- Shared HuggingFace cache used by `-hf` model entries
HF_CACHE_DIR=/tank/aimodels/huggingface