Skip to content

feat: infrastructure support for multi-model deployment and isolated gateway routing#1007

Closed
asm582 wants to merge 2 commits intomainfrom
pr1-infra
Closed

feat: infrastructure support for multi-model deployment and isolated gateway routing#1007
asm582 wants to merge 2 commits intomainfrom
pr1-infra

Conversation

@asm582
Copy link
Copy Markdown
Collaborator

@asm582 asm582 commented Apr 14, 2026

This PR enables deploying multiple models in a single namespace. PR was implemented using the Gemini code model.

@asm582
Copy link
Copy Markdown
Collaborator Author

asm582 commented Apr 14, 2026

/ok-to-test

@github-actions
Copy link
Copy Markdown
Contributor

🚀 Kind E2E (full) triggered by /ok-to-test

View the Kind E2E workflow run

@github-actions
Copy link
Copy Markdown
Contributor

🚀 OpenShift E2E — approve and run (/ok-to-test)

View the OpenShift E2E workflow run

@github-actions
Copy link
Copy Markdown
Contributor

GPU Pre-flight Check ✅

GPUs are available for e2e-openshift tests. Proceeding with deployment.

Resource Total Allocated Available
GPUs 50 42 8
Cluster Value
Nodes 16 (7 with GPUs)
Total CPU 993 cores
Total Memory 10383 Gi
GPUs required 4 (min) / 6 (recommended)

@github-actions
Copy link
Copy Markdown
Contributor

GPU Pre-flight Check ✅

GPUs are available for e2e-openshift tests. Proceeding with deployment.

Resource Total Allocated Available
GPUs 50 42 8
Cluster Value
Nodes 16 (7 with GPUs)
Total CPU 993 cores
Total Memory 10383 Gi
GPUs required 4 (min) / 6 (recommended)

1 similar comment
@github-actions
Copy link
Copy Markdown
Contributor

GPU Pre-flight Check ✅

GPUs are available for e2e-openshift tests. Proceeding with deployment.

Resource Total Allocated Available
GPUs 50 42 8
Cluster Value
Nodes 16 (7 with GPUs)
Total CPU 993 cores
Total Memory 10383 Gi
GPUs required 4 (min) / 6 (recommended)

@github-actions
Copy link
Copy Markdown
Contributor

GPU Pre-flight Check ✅

GPUs are available for e2e-openshift tests. Proceeding with deployment.

Resource Total Allocated Available
GPUs 50 36 14
Cluster Value
Nodes 16 (7 with GPUs)
Total CPU 993 cores
Total Memory 10383 Gi
GPUs required 4 (min) / 6 (recommended)

@asm582
Copy link
Copy Markdown
Collaborator Author

asm582 commented Apr 15, 2026

This PR and #1008, #1009 tried to add multi-model infra setup and test with script consolidation. The consolidation touched install scripts that are consumed by other make * test commands. This caused the testing surface to increase due to the tight coupling between the benchmark setup and existing *-test commands, leading to tests failing in CI that do not fail locally; this could still leave non-determinism in the test suite. Hence, I changed the design in #1014 and am closing these PRs for now.

@asm582 asm582 closed this Apr 15, 2026
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.

1 participant