Add read-only support for LLMInferenceService - #198
Open
LogicalGuy77 wants to merge 2 commits into
Open
Conversation
Contributor
Contributor
There was a problem hiding this comment.
Pull request overview
Adds read-only LLMInferenceService visibility for #175.
Changes:
- Adds version-tolerant backend routes and permissions.
- Adds list/detail pages with status, topology, events, and YAML.
- Adds utility, backend, and Cypress tests.
Reviewed changes
Copilot reviewed 21 out of 21 changed files in this pull request and generated 5 comments.
Show a summary per file
| File | Description |
|---|---|
manifests/kustomize/base/cluster-role.yaml |
Grants read access. |
frontend/src/app/types/kfserving/llm-inference-service.ts |
Defines resource types. |
frontend/src/app/types/backend.ts |
Extends response types. |
frontend/src/app/shared/llm-inference-service.utils.ts |
Parses display values. |
frontend/src/app/shared/llm-inference-service.utils.spec.ts |
Tests parsing utilities. |
frontend/src/app/services/backend.service.ts |
Adds client methods. |
frontend/src/app/pages/llm-inference-service/llm-inference-service.module.ts |
Declares pages. |
frontend/src/app/pages/llm-inference-service/llm-inference-service.component.ts |
Implements listing logic. |
frontend/src/app/pages/llm-inference-service/llm-inference-service.component.html |
Renders the list. |
frontend/src/app/pages/llm-inference-service/llm-details/llm-details.component.ts |
Loads resource details. |
frontend/src/app/pages/llm-inference-service/llm-details/llm-details.component.scss |
Styles details. |
frontend/src/app/pages/llm-inference-service/llm-details/llm-details.component.html |
Renders details. |
frontend/src/app/pages/llm-inference-service/config.ts |
Configures table columns. |
frontend/src/app/pages/index/index.component.ts |
Adds navigation. |
frontend/src/app/app.module.ts |
Registers the module. |
frontend/src/app/app-routing.module.ts |
Adds routes. |
frontend/cypress/e2e/llm-inference-service.cy.ts |
Tests browser flows. |
frontend/__mocks__/kubeflow.ts |
Aligns mock typing. |
backend/apps/common/versions.py |
Defines supported versions. |
backend/apps/common/routes/get.py |
Adds read endpoints. |
backend/apps/common/routes/get_test.py |
Tests version detection. |
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
Comment on lines
+65
to
+70
| if (parallelism.dataLocal !== undefined) { | ||
| parts.push(`data-local=${parallelism.dataLocal}`); | ||
| } | ||
| if (parallelism.pipeline !== undefined) { | ||
| parts.push(`pipeline=${parallelism.pipeline}`); | ||
| } |
Contributor
|
Please do a rebase to master (not merge) for a clear commit history. |
Signed-off-by: Harshit Nayan <harshitacademia@gmail.com>
…ing info Signed-off-by: Harshit Nayan <harshitacademia@gmail.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Implements #175. The web application could already display InferenceService and InferenceGraph custom resources but had no visibility into LLMInferenceService, forcing anyone deploying a large language model to fall back to kubectl for basic questions such as whether the resource was accepted, how far the controller had progressed, and what topology and parallelism the specification actually requested. This change is scoped to reading; the create, edit and delete workflows are follow ups.
Assisted-By: Claude noreply@anthropic.com