🚀 Dockerize llamacpp

.devops/full.Dockerfile

@@ -0,0 +1,17 @@
+ARG UBUNTU_VERSION=22.04
+
+FROM ubuntu:$UBUNTU_VERSION as build
+
+RUN apt-get update && \
+    apt-get install -y build-essential python3 python3-pip
+
+RUN pip install --upgrade pip setuptools wheel \
+    && pip install torch torchvision torchaudio sentencepiece numpy
+
+WORKDIR /app
+
+COPY . .
+
+RUN make
+
+ENTRYPOINT ["/app/.devops/tools.sh"]

.devops/main.Dockerfile

@@ -0,0 +1,18 @@
+ARG UBUNTU_VERSION=22.04
+
+FROM ubuntu:$UBUNTU_VERSION as build
+
+RUN apt-get update && \
+    apt-get install -y build-essential
+
+WORKDIR /app
+
+COPY . .
+
+RUN make
+
+FROM ubuntu:$UBUNTU_VERSION as runtime
+
+COPY --from=build /app/main /main
+
+ENTRYPOINT [ "/main" ]

.devops/tools.sh

@@ -0,0 +1,24 @@
+#!/bin/bash
+
+# Read the first argument into a variable
+arg1="$1"
+
+# Shift the arguments to remove the first one
+shift
+
+# Join the remaining arguments into a single string
+arg2="$@"
+
+if [[ $arg1 == '--convert' || $arg1 == '-c' ]]; then
+    python3 ./convert-pth-to-ggml.py $arg2
+elif [[ $arg1 == '--quantize' || $arg1 == '-q' ]]; then
+    /app/quantize $arg2
+elif [[ $arg1 == '--run' || $arg1 == '-r' ]]; then
+    /app/main $arg2
+else
+    echo "Unknown command: $arg1"
+    echo "Available commands: "
+    echo "  --run (-r)"
+    echo "  --convert (-c)"
+    echo "  --quantize (-q)"
+fi

.dockerignore

@@ -0,0 +1,24 @@
+*.o
+*.a
+.cache/
+.vs/
+.vscode/
+.DS_Store
+
+build/
+build-em/
+build-debug/
+build-release/
+build-static/
+build-no-accel/
+build-sanitize-addr/
+build-sanitize-thread/
+
+models/*
+
+/main
+/quantize
+
+arm_neon.h
+compile_commands.json
+Dockerfile

.github/workflows/docker.yml

@@ -0,0 +1,51 @@
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+# GitHub recommends pinning actions to a commit SHA.
+# To get a newer version, you will need to update the SHA.
+# You can also reference a tag or branch, but the action may change without warning.
+
+name: Publish Docker image
+
+on:
+  push:
+    branches:
+      - master
+
+jobs:
+  push_to_registry:
+    name: Push Docker image to Docker Hub
+    runs-on: ubuntu-latest
+
+    strategy:
+      matrix:
+        config:
+          - { tag: "latest", dockerfile: ".devops/main.Dockerfile" }
+          - { tag: "full", dockerfile: ".devops/full.Dockerfile" }
+
+    steps:
+      - name: Check out the repo
+        uses: actions/checkout@v3
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          registry: docker.pkg.github.com
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}  
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v4
+        with:
+          context: .
+          push: true
+          tags: "ghcr.io/ggerganov/llama.cpp:${{ matrix.config.tag }}"
+          file: ${{ matrix.config.dockerfile }}