Skip to content

feat: CE-1579: Add support for deploying serverless with models#276

Open
brosenpod wants to merge 1 commit into
runpod:mainfrom
brosenpod:ce1579
Open

feat: CE-1579: Add support for deploying serverless with models#276
brosenpod wants to merge 1 commit into
runpod:mainfrom
brosenpod:ce1579

Conversation

@brosenpod
Copy link
Copy Markdown
Collaborator

CE-1579: Add support for deploying serverless with models

runpodctl was not previously able to deploy a serverless endpoint with a model attached. Normal serverless deploy uses REST API, but REST API also does not support this. When runpodctl is asked to deploy a serverless endpoint with a model it will instead talk to GraphQL for the deploy. While this bifurcation is not optimal, we already do this when deploying from the Hub.

@promptless
Copy link
Copy Markdown

promptless Bot commented May 7, 2026

Promptless prepared a documentation update related to this change.

Triggered by PR #276

Added documentation for the new --model-reference flag to the runpodctl serverless reference page, including an example and flag description noting the template-id and GPU requirements.

Review: Document --model-reference flag for serverless create

Copy link
Copy Markdown
Member

@TimPietruskyRunPod TimPietruskyRunPod left a comment

Choose a reason for hiding this comment

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

nice approach — reusing the existing GQL path for model references makes sense. a few things to address before this is ready.

Comment thread cmd/pod/list.go Outdated
Comment thread internal/api/endpoints.go
Comment thread cmd/serverless/create.go
Comment thread cmd/serverless/create.go
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.

2 participants