-
Notifications
You must be signed in to change notification settings - Fork 688
feat: add sgl deploy readme #2238
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
Conversation
…ployment instructions
WalkthroughThe documentation for the SGLang backend was updated to indicate that Kubernetes deployment examples are now available. A new README was added under the Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant Documentation
participant Kubernetes Cluster
User->>Documentation: Reads deployment instructions
User->>Kubernetes Cluster: Applies YAML/CRD for SGLang deployment
Kubernetes Cluster-->>User: Deploys SGLang inference graphs as per instructions
Estimated code review effort🎯 2 (Simple) | ⏱️ ~7 minutes Possibly related PRs
Poem
Note ⚡️ Unit Test Generation is now available in beta!Learn more here, or try it out under "Finishing Touches" below. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
Documentation and Community
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actionable comments posted: 2
🧹 Nitpick comments (1)
components/backends/sglang/deploy/README.md (1)
21-22: Remove the stray trailing asterisks in the headingThe extra
**breaks markdown rendering and anchor generation.-### 3. **Disaggregated Deployment** (`disagg.yaml`)** +### 3. **Disaggregated Deployment** (`disagg.yaml`)
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
components/backends/sglang/README.md(1 hunks)components/backends/sglang/deploy/README.md(1 hunks)
🧰 Additional context used
🧠 Learnings (4)
📓 Common learnings
Learnt from: julienmancuso
PR: ai-dynamo/dynamo#2012
File: deploy/cloud/helm/crds/templates/nvidia.com_dynamographdeployments.yaml:1233-1235
Timestamp: 2025-07-18T16:04:47.465Z
Learning: The `stopSignal` field in Kubernetes CRDs like DynamoGraphDeployment and DynamoComponentDeployment is autogenerated by controller-gen when upgrading Kubernetes library versions, and represents expected upstream API changes rather than manual code that needs custom validation.
Learnt from: julienmancuso
PR: ai-dynamo/dynamo#2012
File: deploy/cloud/helm/crds/templates/nvidia.com_dynamocomponentdeployments.yaml:1178-1180
Timestamp: 2025-07-18T16:05:05.534Z
Learning: The stopSignal field under lifecycle in DynamoComponentDeployment CRDs is autogenerated due to Kubernetes library upgrades (k8s.io/api and k8s.io/apimachinery from v0.32.3 to v0.33.1), not a manual design decision by the user.
📚 Learning: crd schemas in files like deploy/cloud/helm/crds/templates/*.yaml are auto-generated from kubernetes...
Learnt from: julienmancuso
PR: ai-dynamo/dynamo#2012
File: deploy/cloud/helm/crds/templates/nvidia.com_dynamocomponentdeployments.yaml:92-98
Timestamp: 2025-07-18T16:04:31.771Z
Learning: CRD schemas in files like deploy/cloud/helm/crds/templates/*.yaml are auto-generated from Kubernetes library upgrades and should not be manually modified as changes would be overwritten during regeneration.
Applied to files:
components/backends/sglang/README.mdcomponents/backends/sglang/deploy/README.md
📚 Learning: the stopsignal field under lifecycle in dynamocomponentdeployment crds is autogenerated due to kuber...
Learnt from: julienmancuso
PR: ai-dynamo/dynamo#2012
File: deploy/cloud/helm/crds/templates/nvidia.com_dynamocomponentdeployments.yaml:1178-1180
Timestamp: 2025-07-18T16:05:05.534Z
Learning: The stopSignal field under lifecycle in DynamoComponentDeployment CRDs is autogenerated due to Kubernetes library upgrades (k8s.io/api and k8s.io/apimachinery from v0.32.3 to v0.33.1), not a manual design decision by the user.
Applied to files:
components/backends/sglang/README.mdcomponents/backends/sglang/deploy/README.md
📚 Learning: the `stopsignal` field in kubernetes crds like dynamographdeployment and dynamocomponentdeployment i...
Learnt from: julienmancuso
PR: ai-dynamo/dynamo#2012
File: deploy/cloud/helm/crds/templates/nvidia.com_dynamographdeployments.yaml:1233-1235
Timestamp: 2025-07-18T16:04:47.465Z
Learning: The `stopSignal` field in Kubernetes CRDs like DynamoGraphDeployment and DynamoComponentDeployment is autogenerated by controller-gen when upgrading Kubernetes library versions, and represents expected upstream API changes rather than manual code that needs custom validation.
Applied to files:
components/backends/sglang/deploy/README.md
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (4)
- GitHub Check: Build and Test - vllm
- GitHub Check: pre-merge-rust (lib/runtime/examples)
- GitHub Check: pre-merge-rust (lib/bindings/python)
- GitHub Check: pre-merge-rust (.)
🔇 Additional comments (2)
components/backends/sglang/README.md (1)
176-180: Deployment section update looks goodThe placeholder has been replaced with a working link to the new Kubernetes guide and the wording now reflects both deployment targets.
No further action needed.components/backends/sglang/deploy/README.md (1)
49-58: Use the canonical GPU resource keyStandard Kubernetes GPU scheduling relies on the extended resource key
nvidia.com/gpu.
Using a baregpukey will be ignored by the Kube-Scheduler unless your CRD/controller translates it.- gpu: "1" + nvidia.com/gpu: "1" ... - gpu: "1" + nvidia.com/gpu: "1"If the DynamoGraphDeployment controller purposely aliases
gpu, please add a short note clarifying that.
…ration details in README.md
|
LGTM. @alec-flowers @tanmayv25 can we make smth like this for vLLM and TRT-LLM /deploy folders too? |
athreesh
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
Summary by CodeRabbit