Add Dockerfile with ROCm support

.gitignore

@@ -46,3 +46,9 @@ instances.yaml.backup
 # cpp
 cpp/_build
 cpp/third-party
+
+# projects
+.tool-versions
+**/*/.classpath
+**/*/.settings
+**/*/.project

CONTRIBUTING.md

@@ -11,18 +11,7 @@ Your contributions will fall into two categories:
     - Search for your issue here: https://github.com/pytorch/serve/issues (look for the "good first issue" tag if you're a first time contributor)
     - Pick an issue and comment on the task that you want to work on this feature.
     - To ensure your changes doesn't break any of the existing features run the sanity suite as follows from serve directory:
-        - Install dependencies (if not already installed)
-          For CPU
-
-          ```bash
-          python ts_scripts/install_dependencies.py --environment=dev
-          ```
-
-         For GPU
-           ```bash
-           python ts_scripts/install_dependencies.py --environment=dev --cuda=cu121
-           ```
-            > Supported cuda versions as cu121, cu118, cu117, cu116, cu113, cu111, cu102, cu101, cu92
+        - [Install dependencies](#Install-TorchServe-for-development) (if not already installed)
         - Install `pre-commit` to your Git flow:
             ```bash
             pre-commit install
@@ -60,26 +49,30 @@ pytest -k  test/pytest/test_mnist_template.py
 
 If you plan to develop with TorchServe and change some source code, you must install it from source code.
 
-Ensure that you have `python3` installed, and the user has access to the site-packages or `~/.local/bin` is added to the `PATH` environment variable.
+1. Clone the repository, including third-party modules, with `git clone --recurse-submodules --remote-submodules [email protected]:pytorch/serve.git`
+2. Ensure that you have `python3` installed, and the user has access to the site-packages or `~/.local/bin` is added to the `PATH` environment variable.
+3. Run the following script from the top of the source directory. NOTE: This script force re-installs `torchserve`, `torch-model-archiver` and `torch-workflow-archiver` if existing installations are found
 
-Run the following script from the top of the source directory.
+    #### For Debian Based Systems/MacOS
 
-NOTE: This script force re-installs `torchserve`, `torch-model-archiver` and `torch-workflow-archiver` if existing installations are found
+    ```
+    python ./ts_scripts/install_dependencies.py --environment=dev
+    python ./ts_scripts/install_from_src.py --environment=dev
+    ```
+    ##### Installing Dependencies for Accelerator Support
+    Use the optional `--rocm` or `--cuda` flag with `install_dependencies.py` for installing accelerator specific dependencies.
 
-#### For Debian Based Systems/ MacOS
-
-```
-python ./ts_scripts/install_dependencies.py --environment=dev
-python ./ts_scripts/install_from_src.py --environment=dev
-```
+    Possible values are
+    - rocm: `rocm61`, `rocm60`
+    - cuda: `cu111`, `cu102`, `cu101`, `cu92`
 
-Use `--cuda` flag with `install_dependencies.py` for installing cuda version specific dependencies. Possible values are `cu111`, `cu102`, `cu101`, `cu92`
+    For example `python ./ts_scripts/install_dependencies.py --environment=dev --rocm=rocm61`
 
-#### For Windows
+    #### For Windows
 
-Refer to the documentation [here](docs/torchserve_on_win_native.md).
+    Refer to the documentation [here](docs/torchserve_on_win_native.md).
 
-For information about the model archiver, see [detailed documentation](model-archiver/README.md).
+    For information about the model archiver, see [detailed documentation](model-archiver/README.md).
 
 ### What to Contribute?
 

README.md

@@ -22,7 +22,10 @@ curl http://127.0.0.1:8080/predictions/bert -T input.txt
 
 ```bash
 # Install dependencies
-# cuda is optional
+python ./ts_scripts/install_dependencies.py
+
+# Include dependencies for accelerator support with the relevant optional flags
+python ./ts_scripts/install_dependencies.py --rocm=rocm61
 python ./ts_scripts/install_dependencies.py --cuda=cu121
 
 # Latest release
@@ -36,7 +39,10 @@ pip install torchserve-nightly torch-model-archiver-nightly torch-workflow-archi
 
 ```bash
 # Install dependencies
-# cuda is optional
+python ./ts_scripts/install_dependencies.py
+
+# Include depeendencies for accelerator support with the relevant optional flags
+python ./ts_scripts/install_dependencies.py --rocm=rocm61
 python ./ts_scripts/install_dependencies.py --cuda=cu121
 
 # Latest release

docker/Dockerfile

@@ -37,12 +37,12 @@ ARG BRANCH_NAME
 ARG REPO_URL=https://github.com/pytorch/serve.git
 ENV PYTHONUNBUFFERED TRUE
 
-RUN --mount=type=cache,id=apt-dev,target=/var/cache/apt \
+RUN --mount=type=cache,sharing=locked,id=apt-dev,target=/var/cache/apt \
     apt-get update && \
     apt-get upgrade -y && \
     apt-get install software-properties-common -y && \
     add-apt-repository -y ppa:deadsnakes/ppa && \
-    apt remove python-pip  python3-pip && \
+    apt remove -y python-pip python3-pip && \
     DEBIAN_FRONTEND=noninteractive apt-get install --no-install-recommends -y \
         ca-certificates \
         g++ \
@@ -55,6 +55,13 @@ RUN --mount=type=cache,id=apt-dev,target=/var/cache/apt \
         git \
     && rm -rf /var/lib/apt/lists/*
 
+RUN --mount=type=cache,sharing=locked,id=apt-dev,target=/var/cache/apt \
+    if [ "$USE_ROCM_VERSION" ]; then \
+        apt-get update && \
+        DEBIAN_FRONTEND=noninteractive apt-get install --no-install-recommends -y rocm-dev amd-smi-lib \
+        && rm -rf /var/lib/apt/lists/* ; \
+    fi
+
 # Make the virtual environment and "activating" it by adding it first to the path.
 # From here on the python$PYTHON_VERSION interpreter is used and the packages
 # are installed in /home/venv which is what we need for the "runtime-image"
@@ -67,6 +74,7 @@ RUN python -m pip install -U pip setuptools
 RUN export USE_CUDA=1
 
 ARG USE_CUDA_VERSION=""
+ARG USE_ROCM_VERSION=""
 
 COPY ./ serve
 
@@ -76,7 +84,6 @@ RUN \
         git clone --recursive $REPO_URL -b $BRANCH_NAME serve; \
     fi
 
-
 WORKDIR "serve"
 
 RUN cp docker/dockerd-entrypoint.sh /usr/local/bin/dockerd-entrypoint.sh
@@ -90,6 +97,14 @@ RUN \
         else \
             python ./ts_scripts/install_dependencies.py;\
         fi; \
+    elif echo "${BASE_IMAGE}" | grep -q "rocm/"; then \
+        # Install ROCm version specific binary when ROCm version is specified as a build arg
+        if [ "$USE_ROCM_VERSION" ]; then \
+            python ./ts_scripts/install_dependencies.py --rocm $USE_ROCM_VERSION;\
+        # Install the binary with the latest CPU image on a ROCm base image
+        else \
+            python ./ts_scripts/install_dependencies.py; \
+        fi; \
     # Install the CPU binary
     else \
         python ./ts_scripts/install_dependencies.py; \
@@ -111,13 +126,14 @@ FROM ${BASE_IMAGE} AS production-image
 # Re-state ARG PYTHON_VERSION to make it active in this build-stage (uses default define at the top)
 ARG PYTHON_VERSION
 ENV PYTHONUNBUFFERED TRUE
+ARG USE_ROCM_VERSION
 
-RUN --mount=type=cache,target=/var/cache/apt \
+RUN --mount=type=cache,sharing=locked,target=/var/cache/apt \
     apt-get update && \
     apt-get upgrade -y && \
     apt-get install software-properties-common -y && \
     add-apt-repository ppa:deadsnakes/ppa -y && \
-    apt remove python-pip  python3-pip && \
+    apt remove -y python-pip python3-pip && \
     DEBIAN_FRONTEND=noninteractive apt-get install --no-install-recommends -y \
     python$PYTHON_VERSION \
     python3-distutils \
@@ -130,13 +146,25 @@ RUN --mount=type=cache,target=/var/cache/apt \
     && rm -rf /var/lib/apt/lists/* \
     && cd /tmp
 
+RUN --mount=type=cache,sharing=locked,id=apt-dev,target=/var/cache/apt \
+    if [ "$USE_ROCM_VERSION" ]; then \
+        apt-get update && \
+        DEBIAN_FRONTEND=noninteractive apt-get install --no-install-recommends -y rocm-dev amd-smi-lib \
+        && rm -rf /var/lib/apt/lists/* ; \
+    fi
+
 RUN useradd -m model-server \
     && mkdir -p /home/model-server/tmp
 
 COPY --chown=model-server --from=compile-image /home/venv /home/venv
 COPY --from=compile-image /usr/local/bin/dockerd-entrypoint.sh /usr/local/bin/dockerd-entrypoint.sh
 ENV PATH="/home/venv/bin:$PATH"
 
+RUN \
+    if [ "$USE_ROCM_VERSION" ]; then \
+        python -m pip install /opt/rocm/share/amd_smi; \
+    fi
+
 RUN chmod +x /usr/local/bin/dockerd-entrypoint.sh \
     && chown -R model-server /home/model-server
 
@@ -157,13 +185,14 @@ FROM ${BASE_IMAGE} AS ci-image
 ARG PYTHON_VERSION
 ARG BRANCH_NAME
 ENV PYTHONUNBUFFERED TRUE
+ARG USE_ROCM_VERSION
 
-RUN --mount=type=cache,target=/var/cache/apt \
+RUN --mount=type=cache,sharing=locked,target=/var/cache/apt \
     apt-get update && \
     apt-get upgrade -y && \
     apt-get install software-properties-common -y && \
     add-apt-repository -y ppa:deadsnakes/ppa && \
-    apt remove python-pip  python3-pip && \
+    apt remove -y python-pip python3-pip && \
     DEBIAN_FRONTEND=noninteractive apt-get install --no-install-recommends -y \
     python$PYTHON_VERSION \
     python3-distutils \
@@ -183,13 +212,24 @@ RUN --mount=type=cache,target=/var/cache/apt \
     && rm -rf /var/lib/apt/lists/* \
     && cd /tmp
 
+RUN --mount=type=cache,sharing=locked,id=apt-dev,target=/var/cache/apt \
+    if [ "$USE_ROCM_VERSION" ]; then \
+        apt-get update && \
+        DEBIAN_FRONTEND=noninteractive apt-get install --no-install-recommends -y rocm-dev amd-smi-lib \
+        && rm -rf /var/lib/apt/lists/* ; \
+    fi
 
 COPY --from=compile-image /home/venv /home/venv
 
 ENV PATH="/home/venv/bin:$PATH"
 
 RUN python -m pip install --no-cache-dir -r https://raw.githubusercontent.com/pytorch/serve/$BRANCH_NAME/requirements/developer.txt
 
+RUN \
+    if [ "$USE_ROCM_VERSION" ]; then \
+        python -m pip install /opt/rocm/share/amd_smi; \
+    fi
+
 RUN mkdir /home/serve
 ENV TS_RUN_IN_DOCKER True
 
@@ -203,11 +243,13 @@ ARG PYTHON_VERSION
 ARG BRANCH_NAME
 ARG BUILD_FROM_SRC
 ARG LOCAL_CHANGES
+ARG USE_ROCM_VERSION
 ARG BUILD_WITH_IPEX
 ARG IPEX_VERSION=1.11.0
 ARG IPEX_URL=https://software.intel.com/ipex-whl-stable
 ENV PYTHONUNBUFFERED TRUE
-RUN --mount=type=cache,target=/var/cache/apt \
+
+RUN --mount=type=cache,sharing=locked,target=/var/cache/apt \
     apt-get update && \
     apt-get upgrade -y && \
     apt-get install software-properties-common -y && \
@@ -227,9 +269,15 @@ RUN --mount=type=cache,target=/var/cache/apt \
     # https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=1009905
     openjdk-17-jdk \
     build-essential \
+    wget \
     curl \
     vim \
     numactl \
+    nodejs \
+    npm \
+    zip \
+    unzip \
+    && npm install -g [email protected] newman-reporter-htmlextra markdown-link-check \
     && if [ "$BUILD_WITH_IPEX" = "true" ]; then apt-get update && apt-get install -y libjemalloc-dev libgoogle-perftools-dev libomp-dev && ln -s /usr/lib/x86_64-linux-gnu/libjemalloc.so /usr/lib/libjemalloc.so && ln -s /usr/lib/x86_64-linux-gnu/libtcmalloc.so /usr/lib/libtcmalloc.so && ln -s /usr/lib/x86_64-linux-gnu/libiomp5.so /usr/lib/libiomp5.so; fi \
     && rm -rf /var/lib/apt/lists/*
 
@@ -243,10 +291,17 @@ RUN \
 
 COPY --from=compile-image /home/venv /home/venv
 ENV PATH="/home/venv/bin:$PATH"
+
+RUN \
+    if [ "$USE_ROCM_VERSION" ]; then \
+        python -m pip install /opt/rocm/share/amd_smi; \
+    fi
+
 WORKDIR "serve"
+
 RUN python -m pip install -U pip setuptools \
     && python -m pip install --no-cache-dir -r requirements/developer.txt \
-    && python ts_scripts/install_from_src.py \
+    && python ts_scripts/install_from_src.py --environment=dev\
     && useradd -m model-server \
     && mkdir -p /home/model-server/tmp \
     && cp docker/dockerd-entrypoint.sh /usr/local/bin/dockerd-entrypoint.sh \