Files
fulloch/Dockerfile_gpu
T
Liam PettigrewandClaude Opus 4.5 464d049433 init
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-23 17:06:44 +11:00

46 lines
1.2 KiB
Plaintext

# Use NVIDIA CUDA base image (includes nvcc compiler for building)
FROM nvidia/cuda:12.4.1-devel-ubuntu22.04
# Avoid interactive prompts during package installation
ENV DEBIAN_FRONTEND=noninteractive
# Install Python 3.12 and build tools
RUN apt-get update && apt-get install -y \
software-properties-common \
&& add-apt-repository ppa:deadsnakes/ppa \
&& apt-get update && apt-get install -y \
python3.12 \
python3.12-venv \
python3.12-dev \
python3-pip \
git \
build-essential \
cmake \
&& rm -rf /var/lib/apt/lists/*
# Set Python 3.12 as default
RUN ln -s /usr/bin/python3.12 /usr/bin/python
WORKDIR /app
# 2. Set Environment Variables to force CUDA build
# -DGGML_CUDA=on is the flag for recent llama-cpp-python versions (0.3.x)
ENV CMAKE_ARGS="-DGGML_CUDA=on"
ENV FORCE_CMAKE=1
COPY requirements.txt .
# 3. Install dependencies
# This will now compile llama-cpp-python with CUDA support
RUN python3.12 -m pip install --upgrade pip && \
python3.12 -m pip install --no-cache-dir -r requirements.txt
# Copy application files (ignoring __pycache__ via .dockerignore)
COPY app.py .
COPY tools/ tools/
COPY utils/ utils/
COPY wav/ wav/
COPY audio/ audio/
CMD ["python3.12", "app.py"]