Files
YG_FT/docker/compute/docker-compose.yml
wuyongtao b28cfbc6fa feat: 更新后端平台模块、Compute引擎、前端组件及构建产物
- 更新 backend 平台 API、platform_store、compute_gateway sync
- 更新 compute agent/engine/adapter 及 API
- 更新 Docker 部署配置(app/compute)
- 新增 frontend/src/utils/ 工具模块
- 新增 scripts/ops_diagnostics.py 运维诊断脚本
- 新增 docs/2026-07-23-development-summary.md 开发总结
- 重构 frontend/dist 构建产物(新 hash)
- 更新前端多个视图组件及 API 模块

Co-Authored-By: Claude <noreply@anthropic.com>
2026-07-23 19:32:42 +08:00

54 lines
2.5 KiB
YAML

services:
compute-api:
image: ${COMPUTE_API_IMAGE:-yg-ft-compute-api:latest}
container_name: yg-ft-compute-api
gpus: all
ports:
- "${COMPUTE_API_PORT:-19100}:9100"
- "${FILE_GATEWAY_PORT:-19101}:9100"
environment:
COMPUTE_ENV: ${COMPUTE_ENV:-prod}
COMPUTE_HOST_ID: ${COMPUTE_HOST_ID:-gpu-node-01}
COMPUTE_EXECUTION_MODE: ${COMPUTE_EXECUTION_MODE:-real}
MODELTF_ROUTE_PREFIX: ${MODELTF_ROUTE_PREFIX:-/modelTF}
COMPUTE_AUTH_ENABLED: ${COMPUTE_AUTH_ENABLED:-true}
COMPUTE_SERVICE_TOKEN: ${COMPUTE_SERVICE_TOKEN:-change_me}
ENABLE_APP_CALLBACK: ${ENABLE_APP_CALLBACK:-false}
LLAMA_FACTORY_HOME: ${LLAMA_FACTORY_HOME:-/app/LLaMA-Factory}
YG_FT_DATA_ROOT: ${YG_FT_DATA_ROOT:-/data/yg-ft}
YG_FT_MODEL_ROOT: ${YG_FT_MODEL_ROOT:-/data/yg-ft/models}
YG_FT_DATASET_ROOT: ${YG_FT_DATASET_ROOT:-/data/yg-ft/datasets}
YG_FT_OUTPUT_ROOT: ${YG_FT_OUTPUT_ROOT:-/data/yg-ft/outputs}
TRAINING_LOG_ROOT: ${TRAINING_LOG_ROOT:-/opt/yg-ft/logs/training}
COMPUTE_GPU_COUNT: ${COMPUTE_GPU_COUNT:-0}
COMPUTE_GPU_NAME: ${COMPUTE_GPU_NAME:-NVIDIA A800-SXM4-80GB}
COMPUTE_GPU_MEMORY_GB: ${COMPUTE_GPU_MEMORY_GB:-80}
COMPUTE_GPU_POWER_LIMIT_W: ${COMPUTE_GPU_POWER_LIMIT_W:-300}
MIN_TRAINING_GPU_MEMORY_GB: ${MIN_TRAINING_GPU_MEMORY_GB:-4}
LOG_DIR: ${LOG_DIR:-/opt/yg-ft/logs/compute}
CUDA_VISIBLE_DEVICES: ${CUDA_VISIBLE_DEVICES:-all}
NVIDIA_VISIBLE_DEVICES: ${NVIDIA_VISIBLE_DEVICES:-all}
NVIDIA_DRIVER_CAPABILITIES: ${NVIDIA_DRIVER_CAPABILITIES:-compute,utility}
PYTHONPATH: /app
volumes:
- ../../compute:/app/compute:ro
- ${YG_FT_DATA_ROOT_HOST:-./data/yg-ft}:${YG_FT_DATA_ROOT:-/data/yg-ft}
- ${YG_FT_MODEL_ROOT_HOST:-./data/yg-ft/models}:${YG_FT_MODEL_ROOT:-/data/yg-ft/models}
- ${YG_FT_DATASET_ROOT_HOST:-./data/yg-ft/datasets}:${YG_FT_DATASET_ROOT:-/data/yg-ft/datasets}
- ${YG_FT_OUTPUT_ROOT_HOST:-./data/yg-ft/outputs}:${YG_FT_OUTPUT_ROOT:-/data/yg-ft/outputs}
- ${COMPUTE_LOG_ROOT_HOST:-./data/yg-ft/logs/compute}:${LOG_DIR:-/opt/yg-ft/logs/compute}
- ${TRAINING_LOG_ROOT_HOST:-./data/yg-ft/logs/training}:${TRAINING_LOG_ROOT:-/opt/yg-ft/logs/training}
networks:
- yg-ft-compute
healthcheck:
test: ["CMD-SHELL", "python -c \"import urllib.request; urllib.request.urlopen('http://127.0.0.1:9100/modelTF/health', timeout=3).read()\""]
interval: 30s
timeout: 5s
retries: 3
start_period: 20s
restart: unless-stopped
networks:
yg-ft-compute:
name: yg-ft-compute