Add KServe inference test suite for Neuron#1356
Add KServe inference test suite for Neuron#1356ybrodsky-rh wants to merge 3 commits intorh-ecosystem-edge:mainfrom
Conversation
|
Warning Rate limit exceeded
To keep reviews running without waiting, you can enable usage-based add-on for your organization. This allows additional reviews beyond the hourly cap. Account admins can enable it under billing. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: ⛔ Files ignored due to path filters (10)
📒 Files selected for processing (6)
✨ Finishing Touches🧪 Generate unit tests (beta)
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. Review rate limit: 0/1 reviews remaining, refill in 41 minutes and 40 seconds.Comment |
Merge order:
|
|
/retest |
Add a new Ginkgo test suite under tests/hw-accel/neuron/kserve/ that validates KServe InferenceService deployment and inference on AWS Neuron hardware with OpenShift AI. Test cases: - kserve-001: Deploy InferenceService and verify Ready state - kserve-002: Send inference request and validate response Depends on eco-goinfra KServe builders (rh-ecosystem-edge/eco-goinfra#1337). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
a2d7cde to
4724a47
Compare
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Summary
tests/hw-accel/neuron/kserve/for validating KServe InferenceService deployment and inference on AWS Neuron hardwareinternal/do/kserve.go) using curl pod approach with retry for Neuron model compilation delaysNeuronConfigwith KServe-specific env vars (model name, namespace, vLLM image, tensor parallel size)Dependencies
Test plan
go build ./tests/hw-accel/neuron/kserve/...compiles (after eco-goinfra dependency is updated)neuron && kserveon ROSA HCP cluster with RHOAI/KServe stack installedneuron && vllmandneuron && metricstests are unaffected🤖 Generated with Claude Code