[CLEANUP]

scripts/hf_tgi/Dockerfile

@@ -0,0 +1,47 @@
+# Use an official Python runtime as a parent image, compatible with the requirements
+FROM python:3.9-slim
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    curl \
+    git \
+    gcc \
+    libssl-dev \
+    unzip \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Rust, which is required for some dependencies
+RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
+
+# Ensure Rust binaries are in the PATH
+ENV PATH="/root/.cargo/bin:${PATH}"
+
+# Install Protoc
+RUN PROTOC_ZIP=protoc-21.12-linux-x86_64.zip \
+    && curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v21.12/$PROTOC_ZIP \
+    && unzip -o $PROTOC_ZIP -d /usr/local bin/protoc \
+    && unzip -o $PROTOC_ZIP -d /usr/local 'include/*' \
+    && rm -f $PROTOC_ZIP
+
+# Clone the text-generation-inference repository and install its dependencies
+RUN git clone https://github.com/huggingface/text-generation-inference.git && cd text-generation-inference \
+    && BUILD_EXTENSIONS=True make install \
+    && cd ..
+
+# Set the environment variable for the model ID
+ENV MODEL=HuggingFaceM4/idefics-80b
+
+# Expose the port the app will run on
+ENV PORT 8000
+EXPOSE 8000
+
+# Define an entry point script to initialize the model serving
+# Adjust the command to match the specific volume and model usage
+ENTRYPOINT ["sh", "-c", "text-generation-launcher --model-id ${MODEL} --port ${PORT}"]
+
+# The Docker run command from the user will specify the GPU settings, shared memory size, port mapping, and volume mapping
+# Example Docker run command provided by the user, adjusted for clarity and to match the Dockerfile's settings:
+# docker run --gpus all --shm-size 1g -p $PORT:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.4 --model-id $MODEL