31 lines
1.2 KiB
Bash
31 lines
1.2 KiB
Bash
# Copy to .env and adjust. All values below are defaults baked into
|
|
# docker-compose.yml — only uncomment/change what you actually want to override.
|
|
|
|
# --- llama.cpp / model ---
|
|
LLAMA_MODEL_FILE=Qwen3.8-27B-UD-Q4_K_XL.gguf
|
|
LLAMA_GPU_LAYERS=999
|
|
# 65536 (64K) fits comfortably in 32GB VRAM alongside the model weights.
|
|
# Raise toward 131072 if you need more context; see docs/research/qwen3.8-27b-quant.md
|
|
# for the VRAM math at larger context sizes.
|
|
LLAMA_CTX_SIZE=65536
|
|
|
|
# --- Open WebUI ---
|
|
WEBUI_PORT=8008
|
|
# Required — create an "openwebui" virtual key in LiteLLM's Admin UI first
|
|
# (see docs/proxy-key-onboarding.md), then paste it here.
|
|
OPENWEBUI_LITELLM_KEY=
|
|
|
|
# --- Lazytainer ---
|
|
# Seconds of inactivity before llama-server is stopped. 900 = 15 min.
|
|
LAZYTAINER_INACTIVE_TIMEOUT=900
|
|
|
|
# --- LiteLLM proxy (see docs/proxy-key-onboarding.md, docs/network-access.md) ---
|
|
LITELLM_PORT=4000
|
|
# Required — generate real random values before first run, e.g. `openssl rand -hex 32`.
|
|
# LITELLM_SALT_KEY encrypts stored data; do not change it after the first run
|
|
# (existing encrypted data becomes unreadable if you do).
|
|
# Required — generate a real random value before first run, e.g. `openssl rand -hex 32`.
|
|
LITELLM_MASTER_KEY=
|
|
LITELLM_SALT_KEY=
|
|
LITELLM_DB_PASSWORD=
|