feat: Add tool to deploy LLM models to Cloud Run #124
Closed
Conversation
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
oded996
changed the title
steren
requested changes
Aug 28, 2025
Collaborator
steren
left a comment
steren
left a comment
There was a problem hiding this comment.
Thanks for the PR
While I like the idea. I wonder if we should add it. What are the use cases for an Agent deploying a model?
Note that later, we will have presets that will cover this use case.
| ); | ||
|
|
||
| server.registerTool( | ||
| 'cloud_run_deploy_model', |
Collaborator
There was a problem hiding this comment.
remove the cloud_run_ prefix.
Suggestion: deploy_ai_model
| framework: | ||
| z.enum(['ollama', 'vllm']).describe('The framework to use for serving the model.'), | ||
| model: | ||
| z.string().describe('The model to deploy from Ollama library or Hugging Face Hub.'), |
Collaborator
There was a problem hiding this comment.
Can you add more details. give examples of accepted formats
Refactors the vLLM deployment strategy to use a dedicated Cloud Function for streaming models from Hugging Face to GCS. This avoids slow local downloads and network bottlenecks. Also includes: - Hardening the vLLM container with --max-model-len and HF_HUB_OFFLINE. - Correcting the container port to 8000. - Cleaning up unused code in the deployment scripts.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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Outdated suggestions cannot be applied.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.
This PR introduces a new tool,
cloud-run-deploy-model, which simplifies the deployment of Large Language Models (LLMs) to Google Cloud Run.Key Features:
cloud-run-deploy-modeltool that supports deploying models using the Ollama and vLLM frameworks.Example
Prompt:
Output: