Merge pull request #50 from lordmathis/feat/docker-image

feat: Add Dockerfiles for running llamactl in docker

.dockerignore

@@ -0,0 +1,45 @@
+# Git and version control
+.git/
+.gitignore
+
+# Documentation
+*.md
+docs/
+
+# Development files
+.vscode/
+.idea/
+
+# Build artifacts
+webui/node_modules/
+webui/dist/
+webui/.next/
+*.log
+*.tmp
+
+# Data directories
+data/
+models/
+logs/
+
+# Test files
+*_test.go
+**/*_test.go
+
+# CI/CD
+.github/
+
+# Local configuration
+llamactl.yaml
+config.yaml
+.env
+.env.local
+
+# OS files
+.DS_Store
+Thumbs.db
+
+# Backup files
+*.bak
+*.backup
+*~

README.md

@@ -95,7 +95,30 @@ sudo mv llamactl /usr/local/bin/
 # Windows - Download from releases page
 ```
 
-### Option 2: Build from Source
+### Option 2: Docker (No local backend installation required)
+
+```bash
+# Clone repository and build Docker images
+git clone https://github.com/lordmathis/llamactl.git
+cd llamactl
+mkdir -p data/llamacpp data/vllm models
+
+# Build and start llamactl with llama.cpp CUDA backend
+docker-compose -f docker/docker-compose.yml up llamactl-llamacpp -d
+
+# Build and start llamactl with vLLM CUDA backend
+docker-compose -f docker/docker-compose.yml up llamactl-vllm -d
+
+# Build from source using multi-stage build
+docker build -f docker/Dockerfile.source -t llamactl:source .
+```
+
+**Features:** CUDA support, automatic latest release installation, no backend dependencies.
+**Note:** Dockerfiles are configured for CUDA. Adapt base images for other platforms (CPU, ROCm, etc.).
+
+For detailed Docker setup and configuration, see the [Installation Guide](docs/getting-started/installation.md).
+
+### Option 3: Build from Source
 Requires Go 1.24+ and Node.js 22+
 ```bash
 git clone https://github.com/lordmathis/llamactl.git
@@ -147,9 +170,9 @@ pip install vllm
 # Or use Docker - no local installation required
 ```
 
-## Docker Support
+## Backend Docker Support
 
-llamactl supports running backends in Docker containers - perfect for production deployments without local backend installation. Simply enable Docker in your configuration:
+llamactl can run backends in Docker containers:
 
 ```yaml
 backends:

docker/Dockerfile.llamacpp

@@ -0,0 +1,23 @@
+FROM ghcr.io/ggml-org/llama.cpp:server-cuda
+
+# Install curl for downloading llamactl
+RUN apt-get update && apt-get install -y curl && rm -rf /var/lib/apt/lists/*
+
+# Download and install the latest llamactl release
+RUN LATEST_VERSION=$(curl -s https://api.github.com/repos/lordmathis/llamactl/releases/latest | grep '"tag_name":' | sed -E 's/.*"([^"]+)".*/\1/') && \
+    curl -L "https://github.com/lordmathis/llamactl/releases/download/${LATEST_VERSION}/llamactl-${LATEST_VERSION}-linux-amd64.tar.gz" | tar -xz && \
+    mv llamactl /usr/local/bin/ && \
+    chmod +x /usr/local/bin/llamactl
+
+# Set working directory
+RUN mkdir -p /data
+WORKDIR /data
+
+# Expose the default llamactl port
+EXPOSE 8080
+
+ENV LLAMACTL_LLAMACPP_COMMAND=/app/llama-server
+ENV LD_LIBRARY_PATH="/app:/usr/local/lib:/usr/lib"
+
+# Set llamactl as the entrypoint
+ENTRYPOINT ["llamactl"]

docker/Dockerfile.source

@@ -0,0 +1,64 @@
+# WebUI build stage
+FROM node:20-alpine AS webui-builder
+
+WORKDIR /webui
+
+# Copy webui package files
+COPY webui/package*.json ./
+
+# Install dependencies
+RUN npm ci
+
+# Copy webui source
+COPY webui/ ./
+
+# Build webui
+RUN npm run build
+
+# Go build stage
+FROM golang:1.24-alpine AS builder
+
+# Install build dependencies
+RUN apk add --no-cache git ca-certificates
+
+# Set working directory
+WORKDIR /build
+
+# Copy go mod files
+COPY go.mod go.sum ./
+
+# Download dependencies
+RUN go mod download
+
+# Copy source code
+COPY cmd/ ./cmd/
+COPY pkg/ ./pkg/
+COPY apidocs/ ./apidocs/
+COPY webui/webui.go ./webui/
+
+# Copy built webui from webui-builder
+COPY --from=webui-builder /webui/dist ./webui/dist
+
+# Build the application
+RUN CGO_ENABLED=0 GOOS=linux go build -a -installsuffix cgo -ldflags="-w -s" -o llamactl ./cmd/server
+
+# Final stage
+FROM alpine:latest
+
+# Install runtime dependencies
+RUN apk --no-cache add ca-certificates
+
+# Create data directory
+RUN mkdir -p /data
+
+# Set working directory
+WORKDIR /data
+
+# Copy binary from builder
+COPY --from=builder /build/llamactl /usr/local/bin/llamactl
+
+# Expose the default port
+EXPOSE 8080
+
+# Set llamactl as the entrypoint
+ENTRYPOINT ["llamactl"]

docker/Dockerfile.vllm

@@ -0,0 +1,20 @@
+FROM vllm/vllm-openai:latest
+
+# Install curl for downloading llamactl
+RUN apt-get update && apt-get install -y curl && rm -rf /var/lib/apt/lists/*
+
+# Download and install the latest llamactl release
+RUN LATEST_VERSION=$(curl -s https://api.github.com/repos/lordmathis/llamactl/releases/latest | grep '"tag_name":' | sed -E 's/.*"([^"]+)".*/\1/') && \
+    curl -L "https://github.com/lordmathis/llamactl/releases/download/${LATEST_VERSION}/llamactl-${LATEST_VERSION}-linux-amd64.tar.gz" | tar -xz && \
+    mv llamactl /usr/local/bin/ && \
+    chmod +x /usr/local/bin/llamactl
+
+# Set working directory
+RUN mkdir -p /data
+WORKDIR /data
+
+# Expose the default llamactl port
+EXPOSE 8080
+
+# Set llamactl as the entrypoint
+ENTRYPOINT ["llamactl"]

docker/docker-compose.yml

@@ -0,0 +1,56 @@
+version: '3.8'
+
+services:
+  llamactl-llamacpp:
+    build:
+      context: ..
+      dockerfile: docker/Dockerfile.llamacpp
+    image: llamactl:llamacpp-cuda
+    container_name: llamactl-llamacpp
+    ports:
+      - "8080:8080"
+    volumes:
+      - ./data/llamacpp:/data
+      - ./models:/models  # Mount models directory
+      - ~/.cache/llama.cpp:/root/.cache/llama.cpp  # Llama.cpp cache
+    environment:
+      # Set data directory for persistence
+      - LLAMACTL_DATA_DIR=/data
+      # Enable Docker mode for nested containers (if needed)
+      - LLAMACTL_LLAMACPP_DOCKER_ENABLED=false
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+    restart: unless-stopped
+
+  llamactl-vllm:
+    build:
+      context: ..
+      dockerfile: docker/Dockerfile.vllm
+    image: llamactl:vllm-cuda
+    container_name: llamactl-vllm
+    ports:
+      - "8081:8080"  # Use different port to avoid conflicts
+    volumes:
+      - ./data/vllm:/data
+      - ./models:/models  # Mount models directory
+      - ~/.cache/huggingface:/root/.cache/huggingface  # HuggingFace cache
+    environment:
+      # Set data directory for persistence
+      - LLAMACTL_DATA_DIR=/data
+      # Enable Docker mode for nested containers (if needed)
+      - LLAMACTL_VLLM_DOCKER_ENABLED=false
+      # vLLM specific environment variables
+      - CUDA_VISIBLE_DEVICES=all
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+    restart: unless-stopped

docs/getting-started/installation.md

@@ -71,7 +71,72 @@ sudo mv llamactl /usr/local/bin/
 # Windows - Download from releases page
 ```
 
-### Option 2: Build from Source
+### Option 2: Docker
+
+llamactl provides Dockerfiles for creating Docker images with backends pre-installed. The resulting images include the latest llamactl release with the respective backend.
+
+**Available Dockerfiles (CUDA):**
+- **llamactl with llama.cpp CUDA**: `docker/Dockerfile.llamacpp` (based on `ghcr.io/ggml-org/llama.cpp:server-cuda`)
+- **llamactl with vLLM CUDA**: `docker/Dockerfile.vllm` (based on `vllm/vllm-openai:latest`)
+- **llamactl built from source**: `docker/Dockerfile.source` (multi-stage build with webui)
+
+**Note:** These Dockerfiles are configured for CUDA. For other platforms (CPU, ROCm, Vulkan, etc.), adapt the base image. For llama.cpp, see available tags at [llama.cpp Docker docs](https://github.com/ggml-org/llama.cpp/blob/master/docs/docker.md). For vLLM, check [vLLM docs](https://docs.vllm.ai/en/v0.6.5/serving/deploying_with_docker.html).
+
+#### Using Docker Compose
+
+```bash
+# Clone the repository
+git clone https://github.com/lordmathis/llamactl.git
+cd llamactl
+
+# Create directories for data and models
+mkdir -p data/llamacpp data/vllm models
+
+# Start llamactl with llama.cpp backend
+docker-compose -f docker/docker-compose.yml up llamactl-llamacpp -d
+
+# Or start llamactl with vLLM backend
+docker-compose -f docker/docker-compose.yml up llamactl-vllm -d
+```
+
+Access the dashboard at:
+- llamactl with llama.cpp: http://localhost:8080
+- llamactl with vLLM: http://localhost:8081
+
+#### Using Docker Build and Run
+
+**llamactl with llama.cpp CUDA:**
+```bash
+docker build -f docker/Dockerfile.llamacpp -t llamactl:llamacpp-cuda .
+docker run -d \
+  --name llamactl-llamacpp \
+  --gpus all \
+  -p 8080:8080 \
+  -v ~/.cache/llama.cpp:/root/.cache/llama.cpp \
+  llamactl:llamacpp-cuda
+```
+
+**llamactl with vLLM CUDA:**
+```bash
+docker build -f docker/Dockerfile.vllm -t llamactl:vllm-cuda .
+docker run -d \
+  --name llamactl-vllm \
+  --gpus all \
+  -p 8080:8080 \
+  -v ~/.cache/huggingface:/root/.cache/huggingface \
+  llamactl:vllm-cuda
+```
+
+**llamactl built from source:**
+```bash
+docker build -f docker/Dockerfile.source -t llamactl:source .
+docker run -d \
+  --name llamactl \
+  -p 8080:8080 \
+  llamactl:source
+```
+
+### Option 3: Build from Source
 
 Requirements:
 - Go 1.24 or later