Skip to content

Conversation

@grahamking
Copy link
Contributor

@grahamking grahamking commented Jul 11, 2025

pip install -e . (from the root) and dynamo-frontend is now the Python equivalent of dynamo-run in=http out=dyn.

No need to build or install the dynamo-run Rust binary. This will have the same performance as dynamo-run, it uses the Rust library.

In time we could split http server, pre-processor and router into separate bindings, and call them here, allow easy customization.

Temporarily the directory is components/ingress because from components.frontend import .. conflicts with some examples.

@coderabbitai
Copy link
Contributor

coderabbitai bot commented Jul 11, 2025

Walkthrough

A new CLI command, frontend, has been added to the main CLI application. This command launches a frontend node that starts an OpenAI-compatible HTTP server with features such as engine auto-discovery, prompt pre-processing, and request routing. The implementation includes Typer and argparse entry points, and utilizes asynchronous execution with uvloop.

Changes

File(s) Change Summary
.../cli/cli.py Registered a new CLI command frontend and imported the corresponding function.
.../cli/frontend.py Added a new module implementing the frontend command, with Typer and argparse entry points, and async server logic.

Sequence Diagram(s)

sequenceDiagram
    participant User
    participant CLI (Typer)
    participant Frontend Module
    participant DistributedRuntime
    participant Engine
    participant HTTP Server

    User->>CLI (Typer): dynamo frontend [options]
    CLI (Typer)->>Frontend Module: Invoke frontend()
    Frontend Module->>Frontend Module: Parse options (port, cache size)
    Frontend Module->>DistributedRuntime: Initialize runtime
    Frontend Module->>Engine: make_engine (with options)
    Engine->>Engine: Initialize engine (auto-discovery, etc.)
    Frontend Module->>HTTP Server: run_input()
    HTTP Server-->>User: Serve HTTP requests (OpenAI-compatible)
Loading

Poem

🐇
A frontend hops into the scene,
With engines found and prompts kept clean.
HTTP requests now swiftly flow,
Through round-robin paths they go.
With Typer’s call and uvloop’s might,
The server’s up—oh what a sight!
🥕


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.

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Explain this complex logic.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai explain this code block.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and explain its main purpose.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

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

Actionable comments posted: 2

📜 Review details

Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 26d7a61 and 4b8c890.

📒 Files selected for processing (2)
  • deploy/sdk/src/dynamo/sdk/cli/cli.py (2 hunks)
  • deploy/sdk/src/dynamo/sdk/cli/frontend.py (1 hunks)
🧰 Additional context used
🧬 Code Graph Analysis (1)
deploy/sdk/src/dynamo/sdk/cli/cli.py (1)
deploy/sdk/src/dynamo/sdk/cli/frontend.py (2)
  • cli (31-45)
  • frontend (22-27)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
  • GitHub Check: Build and Test - vllm
🔇 Additional comments (5)
deploy/sdk/src/dynamo/sdk/cli/cli.py (2)

27-27: LGTM: Import statement is correctly placed.

The import follows the existing alphabetical ordering pattern and correctly imports the frontend function from the new module.


79-82: LGTM: Command registration follows established patterns.

The registration uses the same context settings as the run command, which is appropriate for a command that needs to handle extra arguments and unknown options. The disabled help option is consistent with the pattern used for similar commands.

deploy/sdk/src/dynamo/sdk/cli/frontend.py (3)

10-18: LGTM: Imports are well-organized and appropriate.

The imports are logically grouped and all appear to be used correctly in the implementation.


22-27: LGTM: Typer command implementation is correct.

The function signature and implementation follow Typer best practices with appropriate defaults and type hints.


67-68: LGTM: Standard Python entry point pattern.

The if __name__ == "__main__" guard is correctly implemented.

@grahamking grahamking changed the title feat(frontend): dynamo frontend alternative to dynamo-run feat(frontend): python frontend.py alternative to dynamo-run Jul 11, 2025
@grahamking grahamking changed the title feat(frontend): python frontend.py alternative to dynamo-run feat(frontend): python frontend alternative to dynamo-run Jul 11, 2025
No need to build or install the `dynamo-run` Rust binary.

This will have the same performance as `dynamo-run`, it uses the Rust
library.

In time we could split http server, pre-processor and router into
separate bindings, and call them here, allow easy customization.
@grahamking
Copy link
Contributor Author

Will resubmit now that I understand what's needed.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants