# neuron.example.toml — example configuration
#
# Copy to /etc/neuron/neuron.toml and adjust for your environment.
#
# Environment variable overrides use NEURON_ prefix with __ separators:
#   NEURON_PORT=13131

port = 13131

# -- Harnesses ---------------------------------------------------------------
# Each [[harnesses]] entry enables an inference engine. Currently only
# "candle" is supported — it runs in-process and uses huggingface/candle
# for inference on local CUDA devices (or CPU when CUDA is unavailable).

[[harnesses]]
name = "candle"

# -- Candle harness settings -------------------------------------------------
# Optional tuning for the candle harness.

[harness.candle]
# HuggingFace cache directory for model weights. When unset, hf-hub's
# default (~/.cache/huggingface) is used.
# hf_cache = "/var/lib/neuron/hf-cache"

# -- Default models ----------------------------------------------------------
# Models listed here are loaded automatically when the neuron service
# activates. Loading is sequential — a slow or failing entry doesn't
# block the rest of the fleet, but it does push out the time before
# neuron starts serving HTTP, so keep the list short. Operators can
# load additional models on demand via POST /models/load.
#
# Make sure data/neuron.service's TimeoutStartSec is generous enough to
# cover the slowest entry's first-time download + materialisation.

# [[default_models]]
# model_id = "Qwen/Qwen3-0.6B-GGUF"
# harness = "candle"
# quant = "Q4_K_M"
# devices = [0]