第一次提交

docker/compute/.env.example

@@ -0,0 +1,23 @@
+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_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
+
+YG_FT_DATA_ROOT=/data/yg-ft
+YG_FT_DATA_ROOT_HOST=/data/yg-ft
+
+LOG_DIR=/opt/yg-ft/logs/compute
+CUDA_VISIBLE_DEVICES=all
+NVIDIA_VISIBLE_DEVICES=all
+NVIDIA_DRIVER_CAPABILITIES=compute,utility

docker/compute/Dockerfile.compute

@@ -0,0 +1,27 @@
+
+FROM hiyouga/llamafactory:latest
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PIP_NO_CACHE_DIR=1
+
+WORKDIR /app
+
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends tini \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY compute/requirements.txt /tmp/requirements.txt
+RUN pip install --upgrade pip -i https://pypi.tuna.tsinghua.edu.cn/simple \
+    && pip install -r /tmp/requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple \
+    && rm -f /tmp/requirements.txt
+
+RUN mkdir -p /opt/yg-ft/logs/compute /opt/yg-ft/logs/training /data/yg-ft /app/LLaMA-Factory \
+    && chmod -R 0775 /opt/yg-ft /data/yg-ft /app/LLaMA-Factory
+
+ENTRYPOINT ["/usr/bin/tini", "--"]
+
+EXPOSE 9100
+
+CMD ["uvicorn", "compute.api.main:app", "--host", "0.0.0.0", "--port", "9100"]

docker/compute/docker-compose.yml

@@ -0,0 +1,39 @@
+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"
+    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_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}
+      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}
+      - ../../runtime/compute/logs:/opt/yg-ft/logs/compute
+      - ../../runtime/compute/training-logs:/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