Add cnn_dailymail processing for summarization, and offline/online run config yamls

[attafosu]

What does this PR do?

Adds example for running endpoints with Llama3.1-8B on vllm server.

Type of change

• Bug fix
• New feature
• Documentation update
• Refactor/cleanup

Related issues

Addresses #53

Testing

• Tests added/updated
• All tests pass locally
• Manual testing completed

Checklist

• Code follows project style
• Pre-commit hooks pass
• Documentation updated (if needed)

[github-actions]

MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅

[gemini-code-assist]

Summary of Changes

Hello @attafosu, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request enhances the examples by integrating Llama3.1-8B for summarization tasks, leveraging a vLLM server. It provides a streamlined process for preparing the necessary cnn_dailymail dataset and includes ready-to-use configuration files for conducting both offline and online performance benchmarks, allowing users to quickly evaluate the model's capabilities.

Highlights

• Llama3.1-8B Example Integration: This PR introduces a new example for running Llama3.1-8B on a vLLM server, demonstrating its use for summarization tasks.
• CNN/DailyMail Dataset Processing: A new Python script (download_cnndm.py) is added to facilitate the download and preparation of the CNN/DailyMail dataset, including support for calibration data.
• Offline and Online Benchmarking: Configuration YAML files (offline_llama3_8b_cnn.yaml and online_llama3_8b_cnn.yaml) are included to enable easy setup and execution of both offline throughput and online performance benchmarks.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[Copilot]

Pull request overview

This PR adds support for benchmarking Llama 3.1-8B on the CNN/DailyMail summarization dataset. It provides configuration files for both offline and online benchmark modes, along with a script to download and preprocess the dataset, and documentation for running the benchmarks.

• Introduces a Python script to download and format the CNN/DailyMail dataset for summarization tasks
• Adds YAML configuration files for offline and online benchmark scenarios
• Provides comprehensive documentation on setting up and running the benchmarks

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 3 comments.

File	Description
examples/05_Llama3.1-8B_Example/download_cnndm.py	Script to download CNN/DailyMail dataset and format it with summarization prompts
examples/05_Llama3.1-8B_Example/offline_llama3_8b_cnn.yaml	Configuration for offline throughput benchmarking
examples/05_Llama3.1-8B_Example/online_llama3_8b_cnn.yaml	Configuration for online latency benchmarking with Poisson load pattern
examples/05_Llama3.1-8B_Example/README.md	Documentation for setting up and running the Llama 3.1-8B benchmarks

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[gemini-code-assist]

Code Review

This pull request adds a new example for running Llama3.1-8B on the cnn_dailymail dataset for summarization tasks. It includes a data processing script and configuration files for both offline and online benchmarking scenarios. The implementation is well-structured and provides a good starting point. My review focuses on improving the clarity and reproducibility of the documentation, increasing the robustness of the data download script, and providing better guidance within the configuration files to help users achieve optimal benchmark results.

[Copilot]

Pull request overview

Copilot reviewed 4 out of 4 changed files in this pull request and generated 2 comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 4 out of 4 changed files in this pull request and generated 3 comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 4 out of 4 changed files in this pull request and generated 1 comment.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[arekay-nv]

Thanks. Please fix the readme and the parameters to the official versions.
Do you plan to do performance measurements in this PR or a followup?

[Copilot]

Pull request overview

Copilot reviewed 4 out of 4 changed files in this pull request and generated 2 comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[attafosu]

Thanks. Please fix the readme and the parameters to the official versions. Do you plan to do performance measurements in this PR or a followup?

Got it. Fixed.
Both Performance and Acc will be in a follow-up PRs.

[Copilot]

Pull request overview

Copilot reviewed 4 out of 4 changed files in this pull request and generated 1 comment.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.