Dockerfile

FROM nvidia/cuda:12.4.1-cudnn-devel-ubuntu22.04

# Build arg for GPU architectures
ARG CUDA_ARCHITECTURES="8.0;8.6"

ENV DEBIAN_FRONTEND=noninteractive

# Install system dependencies
RUN apt update && \
    apt install -y \
    python3 python3-pip git wget curl cmake ninja-build \
    libgl1 libglib2.0-0 ffmpeg && \
    apt clean

WORKDIR /workspace

COPY requirements.txt .

# Upgrade pip first
RUN pip install --upgrade pip setuptools wheel

# Install requirements if exists
RUN pip install -r requirements.txt

# Install PyTorch with CUDA support
RUN pip install --extra-index-url https://download.pytorch.org/whl/cu124 \
    torch==2.6.0+cu124 torchvision==0.21.0+cu124

# Install SageAttention from git (patch GPU detection)
ENV TORCH_CUDA_ARCH_LIST="${CUDA_ARCHITECTURES}"
ENV FORCE_CUDA="1"
ENV MAX_JOBS="1"

COPY <<EOF /tmp/patch_setup.py
import os
with open('setup.py', 'r') as f:
    content = f.read()

# Get architectures from environment variable
arch_list = os.environ.get('TORCH_CUDA_ARCH_LIST')
arch_set = '{' + ', '.join([f'"{arch}"' for arch in arch_list.split(';')]) + '}'

# Replace the GPU detection section
old_section = '''compute_capabilities = set()
device_count = torch.cuda.device_count()
for i in range(device_count):
    major, minor = torch.cuda.get_device_capability(i)
    if major < 8:
        warnings.warn(f"skipping GPU {i} with compute capability {major}.{minor}")
        continue
    compute_capabilities.add(f"{major}.{minor}")'''

new_section = 'compute_capabilities = ' + arch_set + '''
print(f"Manually set compute capabilities: {compute_capabilities}")'''

content = content.replace(old_section, new_section)

with open('setup.py', 'w') as f:
    f.write(content)
EOF

RUN git clone https://github.com/thu-ml/SageAttention.git /tmp/sageattention && \
    cd /tmp/sageattention && \
    python3 /tmp/patch_setup.py && \
    pip install --no-build-isolation .

# --- FIX: Copy application code ---
COPY . /workspace
# ----------------------------------

RUN useradd -u 1000 -ms /bin/bash user

RUN chown -R user:user /workspace

RUN mkdir /home/user/.cache && \
    chown -R user:user /home/user/.cache

COPY entrypoint.sh /workspace/entrypoint.sh

ENTRYPOINT ["/workspace/entrypoint.sh"]