[Feat] Add GKE example for lmcache cpu ram + local disk offloading

[dannawang0221]

FILL IN THE PR DESCRIPTION HERE

Add GKE example for lmcache offloading with cpu ram and local disk offloading both enabled. In this example we use local SSD as the local disk through Kubernetes ephemeral storage(emptyDir)

BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE

---

• Make sure the code changes pass the pre-commit checks.
• Sign-off your commit by using -s when doing git commit
• Try to classify PRs for easy understanding of the type of changes, such as [Bugfix], [Feat], and [CI].

Detailed Checklist (Click to Expand)

Thank you for your contribution to production-stack! Before submitting the pull request, please ensure the PR meets the following criteria. This helps us maintain the code quality and improve the efficiency of the review process.

PR Title and Classification

Please try to classify PRs for easy understanding of the type of changes. The PR title is prefixed appropriately to indicate the type of change. Please use one of the following:

• [Bugfix] for bug fixes.
• [CI/Build] for build or continuous integration improvements.
• [Doc] for documentation fixes and improvements.
• [Feat] for new features in the cluster (e.g., autoscaling, disaggregated prefill, etc.).
• [Router] for changes to the vllm_router (e.g., routing algorithm, router observability, etc.).
• [Misc] for PRs that do not fit the above categories. Please use this sparingly.

Note: If the PR spans more than one category, please include all relevant prefixes.

Code Quality

The PR need to meet the following code quality standards:

• Pass all linter checks. Please use pre-commit to format your code. See README.md for installation.
• The code need to be well-documented to ensure future contributors can easily understand the code.
• Please include sufficient tests to ensure the change is stay correct and robust. This includes both unit tests and integration tests.

DCO and Signed-off-by

When contributing changes to this project, you must agree to the DCO. Commits must include a Signed-off-by: header which certifies agreement with the terms of the DCO.

Using -s with git commit will automatically add this header.

What to Expect for the Reviews

We aim to address all PRs in a timely manner. If no one reviews your PR within 5 days, please @-mention one of YuhanLiu11
, Shaoting-Feng or ApostaC.

[gemini-code-assist]

Summary of Changes

Hello @dannawang0221, 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 introduces a new example for deploying vLLM on Google Kubernetes Engine (GKE) with LMCache enabled for both CPU RAM and local disk offloading. This allows for more efficient KV cache management by leveraging local SSDs via Kubernetes ephemeral storage, enhancing the scalability and performance of large language model deployments.

Highlights

• New GKE LMCache Example: Adds a comprehensive example demonstrating how to deploy vLLM on GKE with LMCache utilizing both CPU RAM and local disk for KV cache offloading.
• Local Disk Offloading with emptyDir: The new example specifically uses Kubernetes emptyDir to leverage local SSDs for disk-based KV cache offloading, enhancing performance for large models.
• Enhanced GKE Deployment Scripts: Updates existing GKE deployment scripts to support more flexible configuration of cluster name, version, zone, and accelerator types, including GKE Autopilot provisioning.
• Updated Documentation: Includes a new tutorial guiding users through the setup and verification of the LMCache GKE deployment, ensuring clear instructions for replication.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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. ↩

[dannawang0221]

/assign @YaoJiayi

[dannawang0221]

/assign @saikat-royc

[gemini-code-assist]

Code Review

This pull request adds a new example and documentation for using GKE with lmcache for CPU RAM and local disk offloading. The changes involve updating shell scripts to be more flexible by using environment variables, adding a new Helm values file for the example, and creating new documentation pages.

My review has identified a few issues:

• A critical bug in a Helm template (_helpers.tpl) that introduces a redundant and problematic GPU resource request.
• Several high-severity configuration errors in the new example's values file (values-01-offload-kv-cache-local-disk.yaml), including a typo in livenessProbe and an incorrect runtimeClassName for a GPU-enabled pod.
• Several medium-severity issues, including unquoted variables in shell scripts and documentation, typos, and a broken link in the new markdown files.

I've provided suggestions to fix these issues. Overall, the feature is a good addition, but these corrections are necessary for it to function correctly and for the documentation to be clear and accurate.

[YaoJiayi]

cc @YuhanLiu11 @zerofishnoodles

[dannawang0221]

@YuhanLiu11 @royyhuang I'm getting a FileNotFoundError when enabling Prometheus. Could you suggest the correct value for prometheusMultiprocDir? Thank you!

Error: FileNotFoundError: [Errno 2] No such file or directory: '/tmp/lmcache_prometheus/gauge_livemostrecent_461.db'

[YuhanLiu11]

@YuhanLiu11 @royyhuang I'm getting a FileNotFoundError when enabling Prometheus. Could you suggest the correct value for prometheusMultiprocDir? Thank you!

Error: FileNotFoundError: [Errno 2] No such file or directory: '/tmp/lmcache_prometheus/gauge_livemostrecent_461.db'

@Shaoting-Feng Can you take a look at this error? Seems to be a prometheus error.

[dannawang0221]

Hi @YuhanLiu11 and @royyhuang, all comments have been addressed. The PR is ready for another review and approval. Thanks!

[royyhuang]

LGTM! Thanks for the contribution!