update docker files

1. add docker-npu (Dockerfile and docker-compose.yml)
  2. move cuda docker to docker-cuda and tiny changes to adapt to the new path


Former-commit-id: 5431c1f18aadb072208efe7fd8e36fdcfbf807c2

docker/docker-cuda/Dockerfile

@@ -0,0 +1,49 @@
+# Use the NVIDIA official image with PyTorch 2.3.0
+# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-24-02.html
+FROM nvcr.io/nvidia/pytorch:24.02-py3
+
+# Define installation arguments
+ARG INSTALL_BNB=false
+ARG INSTALL_VLLM=false
+ARG INSTALL_DEEPSPEED=false
+ARG PIP_INDEX=https://pypi.org/simple
+
+# Set the working directory
+WORKDIR /app/LLaMA-Factory
+
+RUN cd /app && \
+    git config --global http.version HTTP/1.1 && \
+    git clone https://github.com/hiyouga/LLaMA-Factory.git && \
+    cd /app/LLaMA-Factory
+
+# Install the requirements
+RUN pip config set global.index-url $PIP_INDEX
+RUN python -m pip install --upgrade pip
+RUN python -m pip install -r requirements.txt
+
+
+# Install the LLaMA Factory
+RUN EXTRA_PACKAGES="metrics"; \
+    if [ "$INSTALL_BNB" = "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},bitsandbytes"; \
+    fi; \
+    if [ "$INSTALL_VLLM" = "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},vllm"; \
+    fi; \
+    if [ "$INSTALL_DEEPSPEED" = "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},deepspeed"; \
+    fi; \
+    pip install -e .[$EXTRA_PACKAGES] && \
+    pip uninstall -y transformer-engine flash-attn
+
+# Set up volumes
+VOLUME [ "/root/.cache/huggingface/", "/app/data", "/app/output" ]
+
+# Expose port 7860 for the LLaMA Board
+EXPOSE 7860
+
+# Expose port 8000 for the API service
+EXPOSE 8000
+
+# Launch LLaMA Board
+CMD [ "llamafactory-cli", "webui" ]

docker/docker-cuda/docker-compose.yml

@@ -0,0 +1,30 @@
+services:
+  llamafactory:
+    build:
+      dockerfile: Dockerfile
+      context: .
+      args:
+        INSTALL_BNB: false
+        INSTALL_VLLM: false
+        INSTALL_DEEPSPEED: false
+        PIP_INDEX: https://pypi.org/simple
+    container_name: llamafactory
+    volumes:
+      - ../../hf_cache:/root/.cache/huggingface/
+      - ../../data:/app/LLaMA-Factory/data
+      - ../../output:/app/LLaMA-Factory/output
+    ports:
+      - "7860:7860"
+      - "8000:8000"
+    ipc: host
+    tty: true
+    stdin_open: true
+    command: bash
+    deploy:
+      resources:
+        reservations:
+          devices:
+          - driver: nvidia
+            count: "all"
+            capabilities: [gpu]
+    restart: unless-stopped