Upload 5 files

.dockerignore

@@ -0,0 +1,12 @@
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+.cache/
+.git/
+.vscode/
+hf_cache/
+models/
+qwenmodel/
+*.ipynb
+.env

.env

@@ -0,0 +1 @@
+HUGGING_FACE_HUB_TOKEN=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

Dockerfile

@@ -0,0 +1,44 @@
+FROM nvidia/cuda:12.1.1-cudnn8-runtime-ubuntu22.04
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+ENV HF_HOME=/cache/huggingface
+ENV HF_HUB_CACHE=/cache/huggingface/hub
+ENV TOKENIZERS_PARALLELISM=false
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    python3 \
+    python3-pip \
+    curl \
+    libglib2.0-0 \
+    libsm6 \
+    libxrender1 \
+    libxext6 \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN ln -s /usr/bin/python3 /usr/bin/python
+
+WORKDIR /app
+
+COPY requirements.txt .
+
+RUN pip install --no-cache-dir --upgrade pip setuptools wheel
+
+RUN pip install --no-cache-dir \
+    torch==2.3.1 \
+    torchvision==0.18.1 \
+    torchaudio==2.3.1 \
+    --index-url https://download.pytorch.org/whl/cu121
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 8000
+
+HEALTHCHECK --interval=30s --timeout=10s --start-period=300s --retries=3 \
+CMD curl -f http://localhost:8000/ready || exit 1
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]

docker-compose.yml

@@ -0,0 +1,46 @@
+services:
+  ui-ai-service:
+
+    shm_size: "8gb"
+    gpus: all
+
+    build:
+      context: .
+      dockerfile: Dockerfile
+      
+    image: ui-ai-service:latest
+
+    container_name: ui-ai-service
+
+    ports:
+      - "8000:8000"
+
+    env_file:
+      - .env
+
+    environment:
+      BASE_MODEL_ID: Qwen/Qwen2.5-VL-3B-Instruct
+      HF_HOME: /cache/huggingface
+      HF_HUB_CACHE: /cache/huggingface/hub
+      TOKENIZERS_PARALLELISM: "false"
+
+    volumes:
+      - hf_cache:/cache/huggingface
+
+    restart: unless-stopped
+
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/ready"]
+      interval: 30s
+      timeout: 10s
+      start_period: 300s
+      retries: 3
+
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "50m"
+        max-file: "5"
+
+volumes:
+  hf_cache:

requirements.txt

@@ -0,0 +1,20 @@
+numpy<2
+
+fastapi==0.111.0
+uvicorn[standard]==0.29.0
+
+
+transformers==4.51.3
+accelerate==0.34.2
+peft==0.12.0
+
+pillow==10.4.0
+qwen-vl-utils==0.0.8
+
+sentencepiece
+protobuf
+safetensors
+einops
+
+requests
+python-dotenv