Add Neuronx TGI image 0.0.27 (#110)

* feat(optimum-neuron): add v0.0.27 recipe

* chore: release Neuronx TGI 0.0.27

huggingface/pytorch/optimum/docker/0.0.27/Dockerfile

@@ -0,0 +1,192 @@
+# Fetch and extract the TGI sources
+FROM alpine AS tgi
+RUN mkdir -p /tgi
+ADD https://github.com/huggingface/text-generation-inference/archive/refs/tags/v3.0.0.tar.gz /tgi/sources.tar.gz
+RUN tar -C /tgi -xf /tgi/sources.tar.gz --strip-components=1
+
+# Fetch also the optimum-neuron sources that contain modified TGI sources
+FROM alpine AS optimum-neuron
+RUN mkdir -p /optimum-neuron
+ADD https://github.com/huggingface/optimum-neuron/archive/refs/tags/v0.0.27.tar.gz /optimum-neuron/sources.tar.gz
+RUN tar -C /optimum-neuron -xf /optimum-neuron/sources.tar.gz --strip-components=1
+
+# Build cargo components (adapted from TGI original Dockerfile)
+# Note: we cannot use the cargo-chef base image as it uses python 3.11
+FROM ubuntu:22.04 AS chef
+
+RUN apt-get update -y \
+ && apt-get install -y --no-install-recommends \
+    curl ca-certificates build-essential \
+    && rm -rf /var/lib/apt/lists/* \
+    && apt-get clean
+
+RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- --default-toolchain 1.80.1 --profile minimal -y
+ENV PATH="/root/.cargo/bin:${PATH}"
+RUN cargo install cargo-chef --locked
+
+WORKDIR /usr/src
+
+ARG CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse
+
+FROM chef AS planner
+COPY /optimum-neuron/text-generation-inference/Cargo.toml Cargo.toml
+COPY --from=tgi /tgi/Cargo.lock Cargo.lock
+COPY --from=tgi /tgi/rust-toolchain.toml rust-toolchain.toml
+COPY --from=tgi /tgi/proto proto
+COPY --from=tgi /tgi/router router
+COPY --from=tgi /tgi/backends backends
+COPY --from=tgi /tgi/launcher launcher
+RUN cargo chef prepare --recipe-path recipe.json
+
+FROM chef AS builder
+
+RUN apt-get update -y \
+ && apt-get install -y --no-install-recommends \
+    unzip python3-dev libssl-dev pkg-config \
+    && rm -rf /var/lib/apt/lists/* \
+    && apt-get clean
+
+RUN PROTOC_ZIP=protoc-21.12-linux-x86_64.zip && \
+    curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v21.12/$PROTOC_ZIP && \
+    unzip -o $PROTOC_ZIP -d /usr/local bin/protoc && \
+    unzip -o $PROTOC_ZIP -d /usr/local 'include/*' && \
+    rm -f $PROTOC_ZIP
+
+COPY /optimum-neuron/text-generation-inference/Cargo.toml Cargo.toml
+COPY --from=planner /usr/src/recipe.json recipe.json
+RUN cargo chef cook --release --recipe-path recipe.json
+
+COPY /optimum-neuron/text-generation-inference/Cargo.toml Cargo.toml
+COPY --from=tgi /tgi/Cargo.lock Cargo.lock
+COPY --from=tgi /tgi/rust-toolchain.toml rust-toolchain.toml
+COPY --from=tgi /tgi/proto proto
+COPY --from=tgi /tgi/router router
+COPY --from=tgi /tgi/backends backends
+COPY --from=tgi /tgi/launcher launcher
+# Remove this line once TGI has fixed the conflict
+RUN cargo update ureq --precise 2.9.7
+RUN cargo build --release
+
+# Python base image
+FROM ubuntu:22.04 AS base
+
+RUN apt-get update -y \
+    && apt-get install -y --no-install-recommends \
+    python3-pip \
+    python3-setuptools \
+    python-is-python3 \
+    && rm -rf /var/lib/apt/lists/* \
+    && apt-get clean
+RUN pip3 --no-cache-dir install --upgrade pip
+
+# Python server build image
+FROM base AS pyserver
+
+RUN apt-get update -y \
+    && apt-get install -y --no-install-recommends \
+    make \
+    python3-venv \
+    && rm -rf /var/lib/apt/lists/* \
+    && apt-get clean
+
+RUN install -d /pyserver
+WORKDIR /pyserver
+COPY --from=optimum-neuron /optimum-neuron/text-generation-inference/server server
+COPY --from=tgi /tgi/proto proto
+RUN pip3 install -r server/build-requirements.txt
+RUN VERBOSE=1 BUILDDIR=/pyserver/build PROTODIR=/pyserver/proto make -C server gen-server
+
+# Neuron base image (used for deployment)
+FROM base AS neuron
+
+# Install system prerequisites
+RUN apt-get update -y \
+    && apt-get install -y --no-install-recommends \
+    gnupg2 \
+    wget \
+    python3-dev \
+    libexpat1 \
+    && rm -rf /var/lib/apt/lists/* \
+    && apt-get clean
+
+RUN echo "deb https://apt.repos.neuron.amazonaws.com jammy main" > /etc/apt/sources.list.d/neuron.list
+RUN wget -qO - https://apt.repos.neuron.amazonaws.com/GPG-PUB-KEY-AMAZON-AWS-NEURON.PUB | apt-key add -
+
+# Install neuronx packages
+RUN apt-get update -y \
+    && apt-get install -y --no-install-recommends \
+    aws-neuronx-dkms=2.18.20.0 \
+    aws-neuronx-collectives=2.22.33.0-d2128d1aa \
+    aws-neuronx-runtime-lib=2.22.19.0-5856c0b42 \
+    aws-neuronx-tools=2.19.0.0 \
+    libxml2 \
+    && rm -rf /var/lib/apt/lists/* \
+    && apt-get clean
+
+ENV PATH="/opt/bin/:/opt/aws/neuron/bin:${PATH}"
+
+RUN pip3 install \
+    neuronx-cc==2.15.143.0 \
+    torch-neuronx==2.1.2.2.3.2 \
+    transformers-neuronx==0.12.313 \
+    libneuronxla==2.0.5347.0 \
+    --extra-index-url=https://pip.repos.neuron.amazonaws.com
+
+# Install HuggingFace packages
+RUN pip3 install \
+    hf_transfer huggingface_hub
+
+# Install optimum-neuron
+COPY --from=optimum-neuron /optimum-neuron optimum-neuron
+RUN pip3 install ./optimum-neuron
+
+# TGI base env
+ENV HUGGINGFACE_HUB_CACHE=/tmp \
+    HF_HUB_ENABLE_HF_TRANSFER=1 \
+    PORT=80
+
+# Disable color logs as they are not supported by CloudWatch
+ENV LOGURU_COLORIZE=NO
+ENV LOG_COLORIZE=0
+
+# Install router
+COPY --from=builder /usr/src/target/release/text-generation-router-v2 /usr/local/bin/text-generation-router
+# Install launcher
+COPY --from=builder /usr/src/target/release/text-generation-launcher /usr/local/bin/text-generation-launcher
+# Install python server
+COPY --from=pyserver /pyserver/build/dist dist
+RUN pip install dist/text_generation_server*.tar.gz
+
+# AWS Sagemaker compatible image
+FROM neuron as sagemaker
+
+COPY --from=optimum-neuron /optimum-neuron/text-generation-inference/sagemaker-entrypoint.sh entrypoint.sh
+RUN chmod +x entrypoint.sh
+
+ENTRYPOINT ["./entrypoint.sh"]
+
+
+RUN apt-get update && apt-get install -y --no-install-recommends curl unzip \
+    && rm -rf /var/lib/apt/lists/*
+RUN HOME_DIR=/root && \
+    pip install requests && \
+    curl -o ${HOME_DIR}/oss_compliance.zip https://aws-dlinfra-utilities.s3.amazonaws.com/oss_compliance.zip && \
+    unzip ${HOME_DIR}/oss_compliance.zip -d ${HOME_DIR}/ && \
+    cp ${HOME_DIR}/oss_compliance/test/testOSSCompliance /usr/local/bin/testOSSCompliance && \
+    chmod +x /usr/local/bin/testOSSCompliance && \
+    chmod +x ${HOME_DIR}/oss_compliance/generate_oss_compliance.sh && \
+    ${HOME_DIR}/oss_compliance/generate_oss_compliance.sh ${HOME_DIR} python && \
+    rm -rf ${HOME_DIR}/oss_compliance*
+
+RUN echo "N.B.: Although this image is released under the Apache-2.0 License, the Dockerfile used to build the image \
+    has an indirect documentation dependency on third party <docutils/tools/editors/emacs/rst.el> project. The \
+    <docutils/tools/editors/emacs/rst.el> project's licensing includes the <GPL v3> license. \
+    \n\n\
+    N.B.: Although this image is released under the Apache-2.0 License, the Dockerfile used to build the image uses the \
+    third party <Text Generation Inference (TGI)> project. The <Text Generation Inference (TGI)> project's licensing \
+    includes the <HFOIL --> https://github.com/huggingface/text-generation-inference/blob/main/LICENSE> \
+    license." > /root/THIRD_PARTY_LICENSES
+
+LABEL dlc_major_version="1"
+LABEL com.amazonaws.ml.engines.sagemaker.dlc.framework.huggingface.tgi="true"
+LABEL com.amazonaws.sagemaker.capabilities.accept-bind-to-port="true"

releases.json

@@ -57,7 +57,7 @@
             {
                 "device": "inf2",
                 "min_version": "0.0.22",
-                "max_version": "0.0.25",
+                "max_version": "0.0.27",
                 "os_version": "ubuntu22.04",
                 "python_version": "py310",
                 "pytorch_version": "2.1.2"
@@ -90,12 +90,11 @@
     "releases": [
         {
             "framework": "TGI",
-            "device": "gpu",
-            "version": "2.4.0",
+            "device": "inf2",
+            "version": "0.0.27",
             "os_version": "ubuntu22.04",
-            "python_version": "py311",
-            "pytorch_version": "2.4.0",
-            "cuda_version": "cu124"
+            "python_version": "py310",
+            "pytorch_version": "2.1.2"
         }
     ]
-}
+}