From 29aaf7b846cec1202d72516e7f755cd3632b6557 Mon Sep 17 00:00:00 2001
From: wangchen615 <Chen.Wang1@ibm.com>
Date: Thu, 17 Apr 2025 21:49:48 +0000
Subject: [PATCH 1/4] Add Dockerfile and benchmark script for containerized
 GuideLLM benchmarking

---
 Dockerfile       | 36 ++++++++++++++++++++++++++++++++++++
 run_benchmark.sh | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 70 insertions(+)
 create mode 100644 Dockerfile
 create mode 100755 run_benchmark.sh

diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..db452a1
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,36 @@
+FROM python:3.11-slim
+
+LABEL org.opencontainers.image.source="https://github.com/neuralmagic/guidellm"
+LABEL org.opencontainers.image.description="GuideLLM Benchmark Container"
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    git \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create non-root user
+RUN useradd -m -u 1000 guidellm
+
+# Set working directory
+WORKDIR /app
+
+# Install GuideLLM
+RUN pip install git+https://github.com/neuralmagic/guidellm.git
+
+# Copy and set up the benchmark script
+COPY run_benchmark.sh /app/
+RUN chmod +x /app/run_benchmark.sh
+
+# Set ownership to non-root user
+RUN chown -R guidellm:guidellm /app
+
+# Switch to non-root user
+USER guidellm
+
+# Healthcheck
+HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
+    CMD curl -f http://localhost:8000/health || exit 1
+
+# Set the entrypoint
+ENTRYPOINT ["/app/run_benchmark.sh"] 
\ No newline at end of file
diff --git a/run_benchmark.sh b/run_benchmark.sh
new file mode 100755
index 0000000..17606a4
--- /dev/null
+++ b/run_benchmark.sh
@@ -0,0 +1,34 @@
+#!/bin/bash
+
+# Required environment variables
+TARGET=${TARGET:-"http://localhost:8000"}
+MODEL=${MODEL:-"neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16"}
+RATE_TYPE=${RATE_TYPE:-"sweep"}
+DATA=${DATA:-"prompt_tokens=256,output_tokens=128"}
+MAX_REQUESTS=${MAX_REQUESTS:-"100"}
+MAX_SECONDS=${MAX_SECONDS:-""}
+
+# Output configuration
+OUTPUT_PATH=${OUTPUT_PATH:-"/results/guidellm_benchmark_results"}
+OUTPUT_FORMAT=${OUTPUT_FORMAT:-"json"}  # Can be json, yaml, or yml
+
+# Build the command
+CMD="guidellm benchmark --target \"${TARGET}\" --model \"${MODEL}\" --rate-type \"${RATE_TYPE}\" --data \"${DATA}\""
+
+# Add optional parameters
+if [ ! -z "${MAX_REQUESTS}" ]; then
+    CMD="${CMD} --max-requests ${MAX_REQUESTS}"
+fi
+
+if [ ! -z "${MAX_SECONDS}" ]; then
+    CMD="${CMD} --max-seconds ${MAX_SECONDS}"
+fi
+
+# Add output path with appropriate extension
+if [ ! -z "${OUTPUT_PATH}" ]; then
+    CMD="${CMD} --output-path \"${OUTPUT_PATH}.${OUTPUT_FORMAT}\""
+fi
+
+# Execute the command
+echo "Running command: ${CMD}"
+eval "${CMD}"

From 9ca1e8f0359ad7c0a16d3b11584a364d05afde9f Mon Sep 17 00:00:00 2001
From: wangchen615 <Chen.Wang1@ibm.com>
Date: Thu, 17 Apr 2025 22:06:44 +0000
Subject: [PATCH 2/4] fix pre-commit issue?

---
 Dockerfile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Dockerfile b/Dockerfile
index db452a1..77919ae 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -33,4 +33,4 @@ HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
     CMD curl -f http://localhost:8000/health || exit 1
 
 # Set the entrypoint
-ENTRYPOINT ["/app/run_benchmark.sh"] 
\ No newline at end of file
+ENTRYPOINT ["/app/run_benchmark.sh"]

From 2fd8c0c0a514514e2be2ac64731b05b5da60a218 Mon Sep 17 00:00:00 2001
From: wangchen615 <Chen.Wang1@ibm.com>
Date: Thu, 17 Apr 2025 21:49:48 +0000
Subject: [PATCH 3/4] Add Dockerfile and benchmark script for containerized
 GuideLLM benchmarking

fix pre-commit issue?

Add Docker build files and update .gitignore
---
 Dockerfile             | 36 ++++++++++++++++++++++++++++++++++++
 build/Dockerfile       | 32 ++++++++++++++++++++++++++++++++
 build/run_benchmark.sh | 35 +++++++++++++++++++++++++++++++++++
 run_benchmark.sh       | 34 ++++++++++++++++++++++++++++++++++
 4 files changed, 137 insertions(+)
 create mode 100644 Dockerfile
 create mode 100644 build/Dockerfile
 create mode 100755 build/run_benchmark.sh
 create mode 100755 run_benchmark.sh

diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..77919ae
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,36 @@
+FROM python:3.11-slim
+
+LABEL org.opencontainers.image.source="https://github.com/neuralmagic/guidellm"
+LABEL org.opencontainers.image.description="GuideLLM Benchmark Container"
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    git \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create non-root user
+RUN useradd -m -u 1000 guidellm
+
+# Set working directory
+WORKDIR /app
+
+# Install GuideLLM
+RUN pip install git+https://github.com/neuralmagic/guidellm.git
+
+# Copy and set up the benchmark script
+COPY run_benchmark.sh /app/
+RUN chmod +x /app/run_benchmark.sh
+
+# Set ownership to non-root user
+RUN chown -R guidellm:guidellm /app
+
+# Switch to non-root user
+USER guidellm
+
+# Healthcheck
+HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
+    CMD curl -f http://localhost:8000/health || exit 1
+
+# Set the entrypoint
+ENTRYPOINT ["/app/run_benchmark.sh"]
diff --git a/build/Dockerfile b/build/Dockerfile
new file mode 100644
index 0000000..1654fe8
--- /dev/null
+++ b/build/Dockerfile
@@ -0,0 +1,32 @@
+FROM python:3.12-slim
+
+LABEL org.opencontainers.image.source="https://github.com/neuralmagic/guidellm"
+LABEL org.opencontainers.image.description="GuideLLM Benchmark Container"
+
+# Install dependencies and set up environment in a single layer
+RUN apt-get update && apt-get install -y \
+    git \
+    curl \
+    && pip install git+https://github.com/neuralmagic/guidellm.git \
+    && useradd -m -u 1000 guidellm \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+# Set working directory
+WORKDIR /app
+
+# Copy and set up the benchmark script
+COPY build/run_benchmark.sh /app/
+
+# Set ownership to non-root user
+RUN chown -R guidellm:guidellm /app
+
+# Switch to non-root user
+USER guidellm
+
+# Healthcheck
+HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
+    CMD curl -f http://localhost:8000/health || exit 1
+
+# Set the entrypoint
+ENTRYPOINT ["/app/run_benchmark.sh"]
diff --git a/build/run_benchmark.sh b/build/run_benchmark.sh
new file mode 100755
index 0000000..1f4dd0c
--- /dev/null
+++ b/build/run_benchmark.sh
@@ -0,0 +1,35 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Required environment variables
+TARGET=${TARGET:-"http://localhost:8000"}
+MODEL=${MODEL:-"neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16"}
+RATE_TYPE=${RATE_TYPE:-"sweep"}
+DATA=${DATA:-"prompt_tokens=256,output_tokens=128"}
+MAX_REQUESTS=${MAX_REQUESTS:-"100"}
+MAX_SECONDS=${MAX_SECONDS:-""}
+
+# Output configuration
+OUTPUT_PATH=${OUTPUT_PATH:-"/results/guidellm_benchmark_results"}
+OUTPUT_FORMAT=${OUTPUT_FORMAT:-"json"}  # Can be json, yaml, or yml
+
+# Build the command
+CMD="guidellm benchmark --target \"${TARGET}\" --model \"${MODEL}\" --rate-type \"${RATE_TYPE}\" --data \"${DATA}\""
+
+# Add optional parameters
+if [ ! -z "${MAX_REQUESTS}" ]; then
+    CMD="${CMD} --max-requests ${MAX_REQUESTS}"
+fi
+
+if [ ! -z "${MAX_SECONDS}" ]; then
+    CMD="${CMD} --max-seconds ${MAX_SECONDS}"
+fi
+
+# Add output path with appropriate extension
+if [ ! -z "${OUTPUT_PATH}" ]; then
+    CMD="${CMD} --output-path \"${OUTPUT_PATH}.${OUTPUT_FORMAT}\""
+fi
+
+# Execute the command
+echo "Running command: ${CMD}"
+eval "${CMD}"
diff --git a/run_benchmark.sh b/run_benchmark.sh
new file mode 100755
index 0000000..17606a4
--- /dev/null
+++ b/run_benchmark.sh
@@ -0,0 +1,34 @@
+#!/bin/bash
+
+# Required environment variables
+TARGET=${TARGET:-"http://localhost:8000"}
+MODEL=${MODEL:-"neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16"}
+RATE_TYPE=${RATE_TYPE:-"sweep"}
+DATA=${DATA:-"prompt_tokens=256,output_tokens=128"}
+MAX_REQUESTS=${MAX_REQUESTS:-"100"}
+MAX_SECONDS=${MAX_SECONDS:-""}
+
+# Output configuration
+OUTPUT_PATH=${OUTPUT_PATH:-"/results/guidellm_benchmark_results"}
+OUTPUT_FORMAT=${OUTPUT_FORMAT:-"json"}  # Can be json, yaml, or yml
+
+# Build the command
+CMD="guidellm benchmark --target \"${TARGET}\" --model \"${MODEL}\" --rate-type \"${RATE_TYPE}\" --data \"${DATA}\""
+
+# Add optional parameters
+if [ ! -z "${MAX_REQUESTS}" ]; then
+    CMD="${CMD} --max-requests ${MAX_REQUESTS}"
+fi
+
+if [ ! -z "${MAX_SECONDS}" ]; then
+    CMD="${CMD} --max-seconds ${MAX_SECONDS}"
+fi
+
+# Add output path with appropriate extension
+if [ ! -z "${OUTPUT_PATH}" ]; then
+    CMD="${CMD} --output-path \"${OUTPUT_PATH}.${OUTPUT_FORMAT}\""
+fi
+
+# Execute the command
+echo "Running command: ${CMD}"
+eval "${CMD}"

From 661e8e4d20b08569b45afaf0461e03fd05de2b92 Mon Sep 17 00:00:00 2001
From: wangchen615 <Chen.Wang1@ibm.com>
Date: Tue, 22 Apr 2025 04:03:46 +0000
Subject: [PATCH 4/4] remote original dockerfile and run_benchmark.sh

---
 Dockerfile       | 36 ------------------------------------
 run_benchmark.sh | 34 ----------------------------------
 2 files changed, 70 deletions(-)
 delete mode 100644 Dockerfile
 delete mode 100755 run_benchmark.sh

diff --git a/Dockerfile b/Dockerfile
deleted file mode 100644
index 77919ae..0000000
--- a/Dockerfile
+++ /dev/null
@@ -1,36 +0,0 @@
-FROM python:3.11-slim
-
-LABEL org.opencontainers.image.source="https://github.com/neuralmagic/guidellm"
-LABEL org.opencontainers.image.description="GuideLLM Benchmark Container"
-
-# Install system dependencies
-RUN apt-get update && apt-get install -y \
-    git \
-    curl \
-    && rm -rf /var/lib/apt/lists/*
-
-# Create non-root user
-RUN useradd -m -u 1000 guidellm
-
-# Set working directory
-WORKDIR /app
-
-# Install GuideLLM
-RUN pip install git+https://github.com/neuralmagic/guidellm.git
-
-# Copy and set up the benchmark script
-COPY run_benchmark.sh /app/
-RUN chmod +x /app/run_benchmark.sh
-
-# Set ownership to non-root user
-RUN chown -R guidellm:guidellm /app
-
-# Switch to non-root user
-USER guidellm
-
-# Healthcheck
-HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
-    CMD curl -f http://localhost:8000/health || exit 1
-
-# Set the entrypoint
-ENTRYPOINT ["/app/run_benchmark.sh"]
diff --git a/run_benchmark.sh b/run_benchmark.sh
deleted file mode 100755
index 17606a4..0000000
--- a/run_benchmark.sh
+++ /dev/null
@@ -1,34 +0,0 @@
-#!/bin/bash
-
-# Required environment variables
-TARGET=${TARGET:-"http://localhost:8000"}
-MODEL=${MODEL:-"neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16"}
-RATE_TYPE=${RATE_TYPE:-"sweep"}
-DATA=${DATA:-"prompt_tokens=256,output_tokens=128"}
-MAX_REQUESTS=${MAX_REQUESTS:-"100"}
-MAX_SECONDS=${MAX_SECONDS:-""}
-
-# Output configuration
-OUTPUT_PATH=${OUTPUT_PATH:-"/results/guidellm_benchmark_results"}
-OUTPUT_FORMAT=${OUTPUT_FORMAT:-"json"}  # Can be json, yaml, or yml
-
-# Build the command
-CMD="guidellm benchmark --target \"${TARGET}\" --model \"${MODEL}\" --rate-type \"${RATE_TYPE}\" --data \"${DATA}\""
-
-# Add optional parameters
-if [ ! -z "${MAX_REQUESTS}" ]; then
-    CMD="${CMD} --max-requests ${MAX_REQUESTS}"
-fi
-
-if [ ! -z "${MAX_SECONDS}" ]; then
-    CMD="${CMD} --max-seconds ${MAX_SECONDS}"
-fi
-
-# Add output path with appropriate extension
-if [ ! -z "${OUTPUT_PATH}" ]; then
-    CMD="${CMD} --output-path \"${OUTPUT_PATH}.${OUTPUT_FORMAT}\""
-fi
-
-# Execute the command
-echo "Running command: ${CMD}"
-eval "${CMD}"