YG_FT/docker/compute/.env.example

COMPUTE_ENV=prod
COMPUTE_HOST_ID=gpu-node-01
COMPUTE_EXECUTION_MODE=real
MODELTF_ROUTE_PREFIX=/modelTF
# Five-digit host ports exposed outside the compute server.
COMPUTE_API_PORT=19100
FILE_GATEWAY_PORT=19101
COMPUTE_API_IMAGE=yg-ft-compute-api:latest

# The application server actively polls Compute API; compute server does not need reverse access.
COMPUTE_AUTH_ENABLED=true
COMPUTE_SERVICE_TOKEN=change_me
ENABLE_APP_CALLBACK=false

# LLaMA-Factory is provided by the official hiyouga/llamafactory base image.
LLAMA_FACTORY_HOME=/app/LLaMA-Factory

# Persistent host directories on the compute server.
# Create these directories before starting docker compose. They are mounted into
# the container so base models, datasets, training outputs and logs survive
# container recreation or image upgrades.
YG_FT_DATA_ROOT=/data/yg-ft
YG_FT_DATA_ROOT_HOST=./data/yg-ft
YG_FT_MODEL_ROOT=/data/yg-ft/models
YG_FT_MODEL_ROOT_HOST=./data/yg-ft/models
YG_FT_DATASET_ROOT=/data/yg-ft/datasets
YG_FT_DATASET_ROOT_HOST=./data/yg-ft/datasets
YG_FT_OUTPUT_ROOT=/data/yg-ft/outputs
YG_FT_OUTPUT_ROOT_HOST=./data/yg-ft/outputs
TRAINING_LOG_ROOT=/opt/yg-ft/logs/training
TRAINING_LOG_ROOT_HOST=./data/yg-ft/logs/training
COMPUTE_LOG_ROOT_HOST=./data/yg-ft/logs/compute

# Optional fallback used when nvidia-smi is unavailable.
# Leave COMPUTE_GPU_COUNT=0 on real GPU servers with working NVIDIA runtime.
COMPUTE_GPU_COUNT=0
COMPUTE_GPU_NAME=NVIDIA A800-SXM4-80GB
COMPUTE_GPU_MEMORY_GB=80
COMPUTE_GPU_POWER_LIMIT_W=300

LOG_DIR=/opt/yg-ft/logs/compute
CUDA_VISIBLE_DEVICES=all
NVIDIA_VISIBLE_DEVICES=all
NVIDIA_DRIVER_CAPABILITIES=compute,utility