Sunflower grpo inference test#9
Merged
PatrickCmd merged 8 commits intodeployfrom Apr 18, 2026
Merged
Conversation
PatrickCmd
force-pushed
the
sunflower_grpo_test
branch
from
91d1200 to
bce45d4
Compare
…ate FastAPI app for production API integration and environment variable management
…date README with new endpoints and usage instructions
- Added package.json for project dependencies and scripts - Created postcss.config.mjs for PostCSS configuration - Added tailwind.config.ts for Tailwind CSS setup with custom theme - Initialized tsconfig.json for TypeScript configuration
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 pull request introduces a comprehensive development and deployment setup for the
sunflower-grpo-inference-vllmproject, integrating both a frontend and backend, and providing infrastructure-as-code for Google Cloud Run deployment. The changes include Dockerization, local development tools, a client utility, and a full Terraform configuration for deploying and managing the service and its dependencies in Google Cloud.The most important changes are:
1. Infrastructure-as-Code for Google Cloud Deployment
2. Dockerization and Multi-Stage Build
Dockerfilethat builds the Next.js frontend, installs Python dependencies usinguv, and assembles a minimal runtime image for deployment, supporting efficient builds and separation of concerns..dockerignorefile to ensure only necessary files are included in the Docker build context, improving build performance and security.3. Local Development and Deployment Tooling
Makefilefor local development with targets for installing dependencies, building the frontend, serving the app with hot-reload, and cleaning up build artifacts.Makefilein thecloudrundirectory for building, pushing, and deploying the Docker image to Cloud Run, as well as for managing Terraform and viewing logs..python-versionfile to specify Python 3.12 for development consistency.4. Client Utility
client.pyscript that allows users to interact with the deployed service via HTTP, streaming, or direct Modal SDK calls, facilitating testing and integration.5. Cloud Run Proxy Directory Setup
.gitignorefor thecloudrundirectory to avoid committing sensitive or transient files related to Terraform and deployment.These changes establish a robust foundation for local development, containerized deployment, and managed cloud infrastructure for the Sunflower GRPO inference service.This pull request makes a minor update to the
modal-deploy/README.mdinstructions, adjusting the example path for the audio file used in the client script to reflect the correct relative location.