Add Binary file support, update docker setup and small fixes

Dockerfile

@@ -1,57 +1,193 @@
-# syntax=docker/dockerfile:1
-FROM python:3.10-bookworm
-
-SHELL ["/bin/bash", "-c"] 
-WORKDIR /src/temp
-
-#Install Featomic
-RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs > installRust.sh \
-    && chmod 700 installRust.sh \
-    && ./installRust.sh -y \
-    && source $HOME/.cargo/env \
-    && pip install git+https://github.com/metatensor/featomic.git
-
-#Install OpenMP
-RUN wget https://download.open-mpi.org/release/open-mpi/v5.0/openmpi-5.0.2.tar.bz2 \
-    && tar -xf openmpi-5.0.2.tar.bz2 \
-    && cd openmpi-5.0.2 \
-    && ./configure --prefix=/usr/local/openmpi5/lib \
-    && make all install \
-    && cd .. \
-	&& rm -R openmpi-5.0.2
-
-ENV PATH=/usr/local/openmpi5/lib/bin:$PATH
-ENV LD_LIBRARY_PATH=/usr/local/openmpi5/lib
-ENV HDF5_DIR=/usr/local/hdf5
-
-#Install HDF5
-RUN wget https://hdf-wordpress-1.s3.amazonaws.com/wp-content/uploads/manual/HDF5/HDF5_1_14_3/src/hdf5-1.14.3.tar.gz \
-    && tar -xf hdf5-1.14.3.tar.gz \
-    && cd hdf5-1.14.3 \
-    && HDF5_MPI="ON" CC=mpicc ./configure --enable-shared --enable-parallel --prefix=/usr/local/hdf5 \
-    && HDF5_DIR=/usr/local/hdf5 make \
-    && HDF5_DIR=/usr/local/hdf5 make install \
-    && cd .. \
-	&& rm -R hdf5-1.14.3
-
-#Install h5py
-RUN HDF5_DIR=/usr/local/hdf5 HDF5_MPI="ON" CC=mpicc pip install --no-cache-dir --no-binary=h5py h5py
-
-RUN apt-get update && apt-get install -y \
-    ninja-build \
-    gfortran \
-	&& rm -rf /var/lib/apt/lists/*
-
-RUN pip install meson cython \
-    && pip install --prefer-binary pyscf
-
-#Install SALTED
-COPY . /src/temp/SALTED-master
-RUN cd /src/temp/SALTED-master \
-    && make \
-    && pip install .
-
-RUN rm -R /src/temp
+# syntax=docker/dockerfile:1.7
+
+ARG PYTHON_IMAGE=python:3.10-slim-bookworm
+ARG OPENMPI_VERSION=4.1.8
+ARG HDF5_VERSION=1.14.3
+
+
+# -----------------------------------------------------------------------------
+# Build MPI and parallel HDF5
+# -----------------------------------------------------------------------------
+FROM ${PYTHON_IMAGE} AS native-builder
+
+ARG OPENMPI_VERSION
+ARG HDF5_VERSION
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+    --mount=type=cache,target=/var/lib/apt/lists,sharing=locked \
+    apt-get update && apt-get install -y --no-install-recommends \
+        build-essential \
+        ca-certificates \
+        curl \
+        gfortran \
+        libevent-dev \
+        libhwloc-dev \
+        libmunge-dev \
+        libpmi2-0-dev \
+        zlib1g-dev
+
+WORKDIR /tmp/build
+
+# Open MPI
+#
+# Use the PMIx version bundled with Open MPI instead of independently
+# combining Open MPI 4.1 with PMIx 6.
+RUN curl -fsSL \
+        "https://download.open-mpi.org/release/open-mpi/v4.1/openmpi-${OPENMPI_VERSION}.tar.gz" \
+        | tar -xz \
+    && cd "openmpi-${OPENMPI_VERSION}" \
+    && ./configure \
+        --prefix=/opt/mpi \
+        --enable-shared \
+        --disable-static \
+        --disable-debug \
+        --enable-builtin-atomics \
+        --disable-mpi-fortran \
+        --disable-oshmem \
+        --with-slurm \
+        --with-pmix=internal \
+        --with-hwloc=/usr \
+        --with-libevent=/usr \
+        --with-zlib=/usr \
+        --without-psm \
+        --without-psm2 \
+    && make -j"$(nproc)" \
+    && make install-strip \
+    && cd /tmp/build \
+    && rm -rf "openmpi-${OPENMPI_VERSION}"
+
+ENV PATH=/opt/mpi/bin:${PATH}
+ENV LD_LIBRARY_PATH=/opt/mpi/lib
+
+# Parallel HDF5
+RUN curl -fsSL \
+        "https://hdf-wordpress-1.s3.amazonaws.com/wp-content/uploads/manual/HDF5/HDF5_1_14_3/src/hdf5-${HDF5_VERSION}.tar.gz" \
+        | tar -xz \
+    && cd "hdf5-${HDF5_VERSION}" \
+    && CC=/opt/mpi/bin/mpicc ./configure \
+        --prefix=/opt/hdf5 \
+        --enable-shared \
+        --disable-static \
+        --enable-parallel \
+    && make -j"$(nproc)" \
+    && make install-strip \
+    && cd /tmp/build \
+    && rm -rf "hdf5-${HDF5_VERSION}"
+
+# Create a runtime-only copy without headers, pkg-config files, static
+# archives, documentation, or HDF5 developer tools.
+RUN mkdir -p /opt/runtime \
+    && cp -a /opt/mpi /opt/runtime/mpi \
+    && cp -a /opt/hdf5 /opt/runtime/hdf5 \
+    && rm -rf \
+        /opt/runtime/mpi/include \
+        /opt/runtime/mpi/share/man \
+        /opt/runtime/mpi/share/doc \
+        /opt/runtime/mpi/lib/pkgconfig \
+        /opt/runtime/hdf5/include \
+        /opt/runtime/hdf5/share \
+        /opt/runtime/hdf5/bin \
+        /opt/runtime/hdf5/lib/pkgconfig \
+    && find /opt/runtime -type f \
+        \( -name '*.a' -o -name '*.la' \) \
+        -delete
+
+
+# -----------------------------------------------------------------------------
+# Build the Python environment
+# -----------------------------------------------------------------------------
+FROM native-builder AS python-builder
+
+ENV HDF5_DIR=/opt/hdf5
+ENV PATH=/opt/venv/bin:/opt/mpi/bin:${PATH}
+ENV LD_LIBRARY_PATH=/opt/mpi/lib:/opt/hdf5/lib
+ENV PIP_DISABLE_PIP_VERSION_CHECK=1
+
+RUN python -m venv /opt/venv
+
+RUN --mount=type=cache,target=/root/.cache/pip \
+    python -m pip install --upgrade \
+        pip \
+        setuptools \
+        wheel \
+        build \
+    && python -m pip install \
+        featomic \
+        numpy \
+        cython \
+        pkgconfig \
+    && MPICC=/opt/mpi/bin/mpicc \
+        python -m pip install \
+            --no-binary=mpi4py \
+            mpi4py \
+    && HDF5_DIR=/opt/hdf5 \
+       HDF5_MPI=ON \
+       CC=/opt/mpi/bin/mpicc \
+        python -m pip install \
+            --no-build-isolation \
+            --no-binary=h5py \
+            h5py \
+    && python -m pip install \
+        meson \
+        packaging \
+        numba \
+        ase \
+        scipy \
+        pyyaml \
+        sympy \
+    && python -m pip install \
+        --prefer-binary \
+        pyscf
+
+# Copy SALTED last so that source-code changes do not invalidate the expensive
+# MPI, HDF5, and Python dependency layers.
+WORKDIR /src/SALTED
+COPY . .
+
+RUN --mount=type=cache,target=/root/.cache/pip \
+    python -m pip install . \
+    && python -m pip uninstall -y \
+        build \
+        cython \
+        meson \
+        pkgconfig \
+        wheel \
+    && find /opt/venv -type d -name '__pycache__' \
+        -prune -exec rm -rf '{}' +
+
+
+# -----------------------------------------------------------------------------
+# Minimal runtime
+# -----------------------------------------------------------------------------
+FROM ${PYTHON_IMAGE} AS runtime
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+    --mount=type=cache,target=/var/lib/apt/lists,sharing=locked \
+    apt-get update && apt-get install -y --no-install-recommends \
+        ca-certificates \
+        libevent-2.1-7 \
+        libevent-pthreads-2.1-7 \
+        libgfortran5 \
+        libhwloc15 \
+        libmunge2 \
+        libpmi2-0 \
+        openssh-client \
+        zlib1g
+
+COPY --from=native-builder /opt/runtime/mpi /opt/mpi
+COPY --from=native-builder /opt/runtime/hdf5 /opt/hdf5
+COPY --from=python-builder /opt/venv /opt/venv
+
+ENV PATH=/opt/venv/bin:/opt/mpi/bin:${PATH}
+ENV LD_LIBRARY_PATH=/opt/mpi/lib:/opt/hdf5/lib
+ENV HDF5_DIR=/opt/hdf5
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
 
 WORKDIR /work
-ENTRYPOINT ["/bin/bash"]
+
+CMD ["/bin/bash"]

docs/binary_models.md

@@ -0,0 +1,107 @@
+# Binary Salted Models
+By running `salted_pack.py`, a single binary file is created that consolidates and serializes multiple data sources (NumPy arrays, HDF5 datasets, and model parameters) into one portable format.
+This simplifies model sharing and enables easier deployment for prediction tasks.
+
+## Usage
+### Creating binary models
+Only a single command is required to transform a newly trained and verified model into the binary `.salted` format.
+The command must be executed from the main project directory:
+
+    salted_pack.py
+
+This will generate a `.salted` file.
+
+### Deploying binary models
+Predictions using a binary model can be performed with:
+
+    predict_from_model.py
+
+**Input arguments**
+| Argument  | Meaning |
+| -------- | --------|
+| model | Path to the `.salted` model file.  |
+| xyz   | Path to the `.xyz` file containing the structure for which the prediction is performed.  |
+| -o     | Output directory for the predicted coefficients (optional, default: `predictions/`)  | 
+
+## Implementation details
+### Basic design
+All integers are little-endian signed 32-bit unless noted; all floating arrays are little-endian float64. All 5-char names are ASCII padded with NUL to 5 bytes.
+General Arrays
+
+In the following every array is encoded using the same scheme:
+
+    def encode_array(NDIMS:int, DIMS:list[int], data):
+      file.write(NDIMS)
+      for dim_size in DIMS:
+        file.write(dim_size)
+      file.write(data)
+
+This results in a datastructure as follows:
+
+    NDIMS (int32)
+    DIMS (int32 * NDIMS)
+    DATA (TYPE OF ARRAY)
+
+The Type of the given array is encoded using the numbers from 0 - 5:
+
+    int32=0
+    int64=1
+    float32=2
+    float64=3
+    str=4
+    bool=5
+
+### Sections in the file
+Now the different sections of the file are explained in more detail:
+#### Container header
+
+    MAGIC (5 bytes): b"SALTD"
+    VERSION (int32)
+    N_BLOCKS (int32)
+    TOC: N_BLOCKS entries of:
+        BLOCK_NAME (5 bytes, NUL-padded)
+        BLOCK_OFFSET (int32): file offset (from start) where the block payload begins
+
+#### AVERG, WIG, FPS, WEIGH
+
+    TYPE (int32) (datatype of the following block)
+    NFILES (int32) (number of arrays in the specific key)
+    FOR EACH FILE
+        encode_array(NDIMS, DIMS, data)
+
+#### FEATS, PROJE
+
+    TYPE (int32): float64
+    NKEYS (int32) — top-level HDF5 group count (sorted)
+    For each top-level key:
+        KEY5 (5 bytes, NUL-padded)
+        NSUB (int32) — number of datasets under this key (sorted)
+        For each sub-key dataset:
+            encode_array(NDIMS, DIMS, data)
+
+#### CONFG
+
+    For each entry in inputs (fixed order in code):
+        KEY5 (5 bytes) — e.g., b"averg", b"ncut\0", …
+        TYPE (int32)
+        VALUE encoded by VAL_TYPE:
+            bool: int32 (0 or 1)
+            int32: int32
+            float64: float64
+            str: SLEN (int32, byte length), then SLEN bytes UTF-8
+
+#### BASIS (Only if pyscf is installed)
+
+    TYPE (int32): float64 (tag for numeric arrays in this block)
+    NELEM (int32): number of elements included
+    For each element:
+        ELEM_ID (int32): PySCF element index
+        Four arrays follow, each preceded by a shape header:
+            contractions_per_shell (int32[])
+                encode_array(NDIMS, DIMS, data)
+            angular_momenta_per_shell (int32[])
+                encode_array(NDIMS, DIMS, data)
+            exponents_per_shell (float64[])
+                encode_array(NDIMS, DIMS, data)
+            coeffs_per_shell (float64[])
+                encode_array(NDIMS, DIMS, data)