Skip to content

feat: add CUJ2 inference demo chat UI and update CUJ2 instructions#151

Merged
mchmarny merged 1 commit intoNVIDIA:mainfrom
yuanchen8911:feat/inference-demo-chat-ui
Feb 19, 2026
Merged

feat: add CUJ2 inference demo chat UI and update CUJ2 instructions#151
mchmarny merged 1 commit intoNVIDIA:mainfrom
yuanchen8911:feat/inference-demo-chat-ui

Conversation

@yuanchen8911
Copy link
Contributor

Summary

Add a browser-based chat UI for testing Dynamo inference deployments and update CUJ2
documentation with chat UI instructions.

Motivation / Context

Provides a simple way to interactively test Dynamo vLLM inference deployments via a
browser chat interface, in addition to the existing curl-based approach.

Fixes: N/A
Related: N/A

Type of Change

  • Bug fix (non-breaking change that fixes an issue)
  • New feature (non-breaking change that adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to change)
  • Documentation update
  • Refactoring (no functional changes)
  • Build/CI/tooling

Component(s) Affected

  • CLI (cmd/eidos, pkg/cli)
  • API server (cmd/eidosd, pkg/api, pkg/server)
  • Recipe engine / data (pkg/recipe)
  • Bundlers (pkg/bundler, pkg/component/*)
  • Collectors / snapshotter (pkg/collector, pkg/snapshotter)
  • Validator (pkg/validator)
  • Core libraries (pkg/errors, pkg/k8s)
  • Docs/examples (docs/, examples/)
  • Other: ____________

Implementation Notes

  • examples/demos/workloads/inference/chat.html — Browser chat UI targeting
    Dynamo's OpenAI-compatible /v1/chat/completions endpoint
  • examples/demos/workloads/inference/chat-server.sh — Single script that starts
    kubectl port-forward and a local proxy server, then serves the chat UI on port 9090
  • examples/demos/cuj2.md — Updated "Test the endpoint" section with chat UI as
    Option 1 and curl as Option 2

Testing

make lint

Tested manually against Dynamo vLLM deployment on H100 EKS cluster.

Risk Assessment

  • Low — Isolated change, well-tested, easy to revert
  • Medium — Touches multiple components or has broader impact
  • High — Breaking change, affects critical paths, or complex rollout

Rollout notes: N/A

Checklist

  • Tests pass locally (make test with -race)
  • Linter passes (make lint)
  • I did not skip/disable tests to make CI green
  • I added/updated tests for new functionality
  • I updated docs if user-facing behavior changed
  • Changes follow existing patterns in the codebase
  • Commits are cryptographically signed (git commit -S) — GPG signing info

Signed-off-by: Yuan Chen <yuanchen97@gmail.com>
@yuanchen8911 yuanchen8911 requested a review from a team as a code owner February 19, 2026 04:46
@yuanchen8911 yuanchen8911 changed the title feat: add inference demo chat UI and update CUJ2 instructions feat: add CUJ2 inference demo chat UI and update CUJ2 instructions Feb 19, 2026
Copy link
Member

@mchmarny mchmarny left a comment

Choose a reason for hiding this comment

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

/lgtm

@mchmarny mchmarny merged commit 9a96d23 into NVIDIA:main Feb 19, 2026
13 checks passed
@mchmarny mchmarny deleted the feat/inference-demo-chat-ui branch February 19, 2026 12:37
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants