Add Containerized Benchmarking Support for GuideLLM (#123)

# Add Containerized Benchmarking Support for GuideLLM

## Description
This PR adds containerization support for GuideLLM benchmarking, making
it easier to run benchmarks in containerized environments. The changes
include:

1. A new `Dockerfile` that:
   - Uses Python 3.11 slim as the base image
   - Installs necessary dependencies, including git and curl
   - Sets up a non-root user for security
   - Includes healthcheck functionality
   - Properly configures the benchmark script

2. A new `run_benchmark.sh` script that:
- Provides a flexible way to run benchmarks with configurable parameters
   - Supports environment variable overrides for customization
   - Handles different output formats (json, yaml)
   - Includes proper error handling and logging

## Testing
The container can be built and tested using:
```bash
docker build -t <container-image-repo>/guidellm-benchmark:latest .
docker run -e TARGET="http://localhost:8000" -e MODEL="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16" <container-image-repo>/guidellm-benchmark:latest
```

## Configuration Options
The container supports the following environment variables:
- `TARGET`: The target endpoint for benchmarking (default:
http://localhost:8000)
- `MODEL`: The model to benchmark (default:
neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16)
- `RATE_TYPE`: The rate type for benchmarking (default: sweep)
- `DATA`: The data configuration (default:
prompt_tokens=256,output_tokens=128)
- `MAX_REQUESTS`: Maximum number of requests (default: 100)
- `MAX_SECONDS`: Maximum duration in seconds
- `OUTPUT_PATH`: Path for output files (default:
/results/guidellm_benchmark_results)
- `OUTPUT_FORMAT`: Output format (json, yaml, or yml)

## Security Considerations
- Uses a non-root user for running the benchmark
- Includes proper file permissions
- Implements healthcheck for container monitoring
- Follows container security best practices

## Related Issues
- Closes #119 
- Closes #111 

## Checklist
- [x] Added Dockerfile with proper security configurations
- [x] Added run_benchmark.sh script with environment variable support
- [x] Added documentation for configuration options
- [x] Tested container build and run
- [x] Followed security best practices

---------

Co-authored-by: Samuel Monson <smonson@redhat.com>

Author: wangchen615

deploy/Containerfile

@@ -0,0 +1,48 @@
+ARG PYTHON=3.13
+
+# Use a multi-stage build to create a lightweight production image
+FROM docker.io/python:${PYTHON}-slim as builder
+
+# Copy repository files
+COPY / /src
+
+# Create a venv and install guidellm
+RUN python3 -m venv /opt/guidellm \
+    && /opt/guidellm/bin/pip install --no-cache-dir /src
+
+# Copy entrypoint script into the venv bin directory
+RUN install -m0755 /src/deploy/entrypoint.sh /opt/guidellm/bin/entrypoint.sh
+
+# Prod image
+FROM docker.io/python:${PYTHON}-slim
+
+# Copy the virtual environment from the builder stage
+COPY --from=builder /opt/guidellm /opt/guidellm
+
+# Add guidellm bin to PATH
+ENV PATH="/opt/guidellm/bin:$PATH"
+
+# Create a non-root user
+RUN useradd -md /results guidellm
+
+# Switch to non-root user
+USER guidellm
+
+# Set working directory
+WORKDIR /results
+
+# Metadata
+LABEL org.opencontainers.image.source="https://github.com/neuralmagic/guidellm" \
+      org.opencontainers.image.description="GuideLLM Performance Benchmarking Container"
+
+# Set the environment variable for the benchmark script
+# TODO: Replace with scenario environment variables
+ENV GUIDELLM_TARGET="http://localhost:8000" \
+    GUIDELLM_MODEL="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16" \
+    GUIDELLM_RATE_TYPE="sweep" \
+    GUIDELLM_DATA="prompt_tokens=256,output_tokens=128" \
+    GUIDELLM_MAX_REQUESTS="100" \
+    GUIDELLM_MAX_SECONDS="" \
+    GUIDELLM_OUTPUT_PATH="/results/results.json"
+
+ENTRYPOINT [ "/opt/guidellm/bin/entrypoint.sh" ]

deploy/entrypoint.sh

@@ -0,0 +1,43 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Path to the guidellm binary
+guidellm_bin="/opt/guidellm/bin/guidellm"
+
+# If we receive any arguments switch to guidellm command
+if [ $# -gt 0 ]; then
+    echo "Running command: guidellm $*"
+    exec $guidellm_bin "$@"
+fi
+
+# Get a list of environment variables that start with GUIDELLM_
+args="$(printenv | cut -d= -f1 | grep -E '^GUIDELLM_')"
+
+# NOTE: Bash array + exec prevent shell escape issues
+CMD=("${guidellm_bin}" "benchmark")
+
+# Parse environment variables for the benchmark command
+for var in $args; do
+    # Remove GUIDELLM_ prefix
+    arg_name="${var#GUIDELLM_}"
+
+    # If there is an extra underscore at the
+    # start than this is a config variable
+    if [ "${arg_name:0:1}" == "_" ]; then
+        continue
+    fi
+
+    # Convert to lowercase
+    arg_name="${arg_name,,}"
+    # Replace underscores with dashes
+    arg_name="${arg_name//_/-}"
+
+    # Add the argument to the command array if set
+    if [ -n "${!var}" ]; then
+        CMD+=("--${arg_name}" "${!var}")
+    fi
+done
+
+# Execute the command
+echo "Running command: ${CMD[*]}"
+exec "${CMD[@]}"