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

docker-compose.yml

@@ -1,30 +0,0 @@
-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/data
-      - ./output:/app/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