wehub-resource-sync
c3749daf48
Tests / test-windows (push) Waiting to run
Tests / test-macos (push) Waiting to run
Tests / test-linux (3.13) (push) Failing after 0s
Tests / test-linux (3.11) (push) Failing after 1s
Tests / lint (push) Failing after 0s
Tests / test-linux (3.9) (push) Failing after 1s
Docker / build (push) Failing after 1s
Docker / build-gpu (push) Failing after 2s
113 lines
4.3 KiB
Docker
113 lines
4.3 KiB
Docker
# syntax=docker/dockerfile:1.7
|
|
|
|
# MemPalace — GPU (NVIDIA CUDA) image.
|
|
#
|
|
# Multi-stage build using uv (the project ships a uv.lock, so we install from
|
|
# the frozen lockfile for reproducible images). The `gpu` extra pulls
|
|
# onnxruntime-gpu, which needs CUDA + cuDNN shared libraries at runtime, so
|
|
# this variant builds on an nvidia/cuda base instead of python:slim.
|
|
#
|
|
# The builder stage is dropped from the final image, so build tools
|
|
# (compilers, apt cache) never reach production — only the uv-managed
|
|
# interpreter and the resolved virtualenv do.
|
|
#
|
|
# Build:
|
|
# docker build -f Dockerfile.gpu -t mempalace:gpu .
|
|
#
|
|
# Run (requires the NVIDIA Container Toolkit on the host):
|
|
# docker run -i --rm --gpus all \
|
|
# -e MEMPALACE_EMBEDDING_DEVICE=cuda \
|
|
# -v mempalace-data:/data mempalace:gpu
|
|
#
|
|
# NOTE: onnxruntime-gpu ties itself to a CUDA major version. If embeddings
|
|
# fail to load on the GPU, align CUDA_IMAGE below with the CUDA release that
|
|
# the resolved onnxruntime-gpu wheel targets (see its release notes), then
|
|
# rebuild.
|
|
|
|
ARG CUDA_IMAGE=nvidia/cuda:12.6.3-cudnn-runtime-ubuntu22.04
|
|
|
|
# --- builder ----------------------------------------------------------------
|
|
FROM ${CUDA_IMAGE} AS builder
|
|
|
|
COPY --from=ghcr.io/astral-sh/uv:0.5 /uv /uvx /bin/
|
|
|
|
# Minimal toolchain for any source-built wheels; dropped before the runtime
|
|
# stage so compilers never ship in the production image.
|
|
RUN apt-get update \
|
|
&& apt-get install -y --no-install-recommends build-essential \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
ARG PYTHON_VERSION=3.12
|
|
ARG EXTRAS="extract,spellcheck,gpu"
|
|
|
|
ENV UV_COMPILE_BYTECODE=1 \
|
|
UV_LINK_MODE=copy \
|
|
UV_PYTHON_INSTALL_DIR=/opt/uv/python \
|
|
UV_PYTHON_PREFERENCE=only-managed
|
|
|
|
WORKDIR /app
|
|
|
|
# Layer 1: dependencies only (no project source). Bind-mounted files keep the
|
|
# project tree out of this layer, so changing source code does not bust the
|
|
# deps cache. The uv-managed interpreter is also installed here, into a
|
|
# stable path that the runtime stage can copy verbatim.
|
|
RUN --mount=type=cache,target=/root/.cache/uv \
|
|
--mount=type=bind,source=pyproject.toml,target=pyproject.toml \
|
|
--mount=type=bind,source=uv.lock,target=uv.lock \
|
|
--mount=type=bind,source=README.md,target=README.md \
|
|
set -e; \
|
|
uv python install ${PYTHON_VERSION}; \
|
|
flags=""; \
|
|
for e in $(echo "${EXTRAS}" | tr ',' ' '); do flags="${flags} --extra ${e}"; done; \
|
|
uv sync --frozen --no-install-project --no-dev --python ${PYTHON_VERSION} ${flags}
|
|
|
|
# Layer 2: the project itself. --no-editable installs mempalace into the
|
|
# venv's site-packages (instead of an .pth pointing at /app), so the runtime
|
|
# stage can copy only /app/.venv and drop the source tree.
|
|
COPY . /app
|
|
RUN --mount=type=cache,target=/root/.cache/uv \
|
|
set -e; \
|
|
flags=""; \
|
|
for e in $(echo "${EXTRAS}" | tr ',' ' '); do flags="${flags} --extra ${e}"; done; \
|
|
uv sync --frozen --no-dev --no-editable ${flags}
|
|
|
|
# --- runtime ----------------------------------------------------------------
|
|
FROM ${CUDA_IMAGE} AS runtime
|
|
|
|
LABEL org.opencontainers.image.title="MemPalace (GPU)" \
|
|
org.opencontainers.image.description="Local-first AI memory with CUDA-accelerated embeddings." \
|
|
org.opencontainers.image.source="https://github.com/MemPalace/mempalace" \
|
|
org.opencontainers.image.licenses="MIT"
|
|
|
|
# ca-certificates only — needed for the lazy HuggingFace model download on
|
|
# first use. No build toolchain in this stage.
|
|
RUN apt-get update \
|
|
&& apt-get install -y --no-install-recommends ca-certificates \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
ENV HOME=/data \
|
|
PATH="/app/.venv/bin:${PATH}" \
|
|
PYTHONUNBUFFERED=1 \
|
|
PYTHONDONTWRITEBYTECODE=1 \
|
|
MEMPALACE_EMBEDDING_DEVICE=cuda
|
|
|
|
# Non-root user owning the data volume.
|
|
RUN groupadd --gid 1000 mempalace \
|
|
&& useradd --uid 1000 --gid 1000 --home-dir /data --create-home mempalace
|
|
|
|
WORKDIR /app
|
|
|
|
# Bring the uv-managed interpreter and the resolved venv across the stage
|
|
# boundary. /opt/uv/python must be copied alongside .venv: the venv's
|
|
# shebangs and binary launcher reference it.
|
|
COPY --from=builder /opt/uv/python /opt/uv/python
|
|
COPY --from=builder --chown=mempalace:mempalace /app/.venv /app/.venv
|
|
COPY --chown=mempalace:mempalace docker-entrypoint.sh /usr/local/bin/docker-entrypoint.sh
|
|
RUN chmod +x /usr/local/bin/docker-entrypoint.sh
|
|
|
|
USER mempalace
|
|
VOLUME ["/data"]
|
|
|
|
ENTRYPOINT ["docker-entrypoint.sh"]
|
|
CMD ["mcp"]
|