Skip to content

[Misc] Refract the structure of VLLMRuntime CRD #479

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 20 commits into from
Jun 7, 2025

Conversation

royyhuang
Copy link
Collaborator

@royyhuang royyhuang commented Jun 3, 2025

  1. Restructure the VLLMRuntime CRD. Now the each option has to belong to one of the following struct, ModelSpec, VLLMConfig, LMCacheConfig, DeploymentConfig. This make sure we don't dump all kinds the options under VLLMRuntimeSpec and keep a clean structure of it.

  2. LoraAdapter spec has also be updated to avoid naming conflict, specifically deploymentSpec renamed to LoraAdapterDeploymentSpec.

  3. I also added a config/default.yaml built by kustomize.

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.

@royyhuang royyhuang requested a review from YuhanLiu11 June 3, 2025 00:31
@@ -5,5 +5,5 @@ apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization
images:
- name: controller
newName: lmcache/operator
newName: 1nfinity/production-stack-controller
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please change this to lmcache docker hub image

- --health-probe-bind-address=:8081
command:
- /manager
image: 1nfinity/production-stack-controller:latest
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Also push this to lmcache docker hub

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done!

Copy link
Collaborator

@YuhanLiu11 YuhanLiu11 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM!

@YuhanLiu11 YuhanLiu11 merged commit ff533f8 into vllm-project:main Jun 7, 2025
7 checks passed
Copy link

Warning

You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!

JustinDuy pushed a commit to JustinDuy/production-stack-1 that referenced this pull request Jun 13, 2025
* add CRD support for production stack

Signed-off-by: royyhuang <[email protected]>

* move opertor to a secondary dir instead of in root dir

Signed-off-by: royyhuang <[email protected]>

* rename api group from serving.vllm.ai to production-stack.vllm.ai

Signed-off-by: royyhuang <[email protected]>

* enable lmcache cpu offloading

Signed-off-by: royyhuang <[email protected]>

* enable lmcache remote cache server offloading

Signed-off-by: royyhuang <[email protected]>

* fix service discorvery issue by adding readiness probe to vllm pod

Signed-off-by: royyhuang <[email protected]>

* fix readiness probe

Signed-off-by: royyhuang <[email protected]>

* restructure runtime crd spec

Signed-off-by: royyhuang <[email protected]>

* add default operator manifest

Signed-off-by: royyhuang <[email protected]>

* move rbac for vllm-router pod to controller

Signed-off-by: royyhuang <[email protected]>

* use service account name defined in vllm-router cr to create service account instead of hardcoding

Signed-off-by: royyhuang <[email protected]>

* update sample loraadapter manifest

Signed-off-by: royyhuang <[email protected]>

* update default controller image

Signed-off-by: royyhuang <[email protected]>

* remove old image name patch

Signed-off-by: royyhuang <[email protected]>

---------

Signed-off-by: royyhuang <[email protected]>
davidgao7 pushed a commit to davidgao7/production-stack that referenced this pull request Jun 26, 2025
* add CRD support for production stack

Signed-off-by: royyhuang <[email protected]>

* move opertor to a secondary dir instead of in root dir

Signed-off-by: royyhuang <[email protected]>

* rename api group from serving.vllm.ai to production-stack.vllm.ai

Signed-off-by: royyhuang <[email protected]>

* enable lmcache cpu offloading

Signed-off-by: royyhuang <[email protected]>

* enable lmcache remote cache server offloading

Signed-off-by: royyhuang <[email protected]>

* fix service discorvery issue by adding readiness probe to vllm pod

Signed-off-by: royyhuang <[email protected]>

* fix readiness probe

Signed-off-by: royyhuang <[email protected]>

* restructure runtime crd spec

Signed-off-by: royyhuang <[email protected]>

* add default operator manifest

Signed-off-by: royyhuang <[email protected]>

* move rbac for vllm-router pod to controller

Signed-off-by: royyhuang <[email protected]>

* use service account name defined in vllm-router cr to create service account instead of hardcoding

Signed-off-by: royyhuang <[email protected]>

* update sample loraadapter manifest

Signed-off-by: royyhuang <[email protected]>

* update default controller image

Signed-off-by: royyhuang <[email protected]>

* remove old image name patch

Signed-off-by: royyhuang <[email protected]>

---------

Signed-off-by: royyhuang <[email protected]>
Signed-off-by: David Gao <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants