chore: Default to pytorch backend in trtllm worker

[rmccorm4]

Overview:

Default to pytorch backend in TRTLLM worker if left unspecified.

• Pytorch backend is currently the only supported path for Deepseek R1
• Pytorch backend seems like best supported path for use of trtllm-llmapi-launch currently
• Only pytorch backend supports kv events/metrics currently

Power users can override backend field in extra engine args YAML if needed.

Summary by CodeRabbit

• New Features
  • Explicitly sets the backend to "pytorch" for the TensorRT-LLM engine configuration.

[coderabbitai]

Walkthrough

A new key-value pair, "backend": "pytorch", is added to the arg_map dictionary in the init asynchronous function within the TensorRT-LLM subprocess module. This update ensures that the backend is explicitly set to "pytorch" during the initial configuration of engine arguments.

Changes

File(s)	Change Summary
launch/dynamo-run/src/subprocess/trtllm_inc.py	Added "backend": "pytorch" to arg_map in init function

Poem

In the land of code where engines ignite,
A backend named PyTorch steps into the light.
With a tweak to the map, the journey's begun,
Now every subprocess knows which backend to run.
🐇✨

---

🪧 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.

[coderabbitai]

Actionable comments posted: 0

🧹 Nitpick comments (1)

launch/dynamo-run/src/subprocess/trtllm_inc.py (1)

355-355: LGTM! Backend default aligns with PyTorch-first strategy.

The change successfully defaults to PyTorch backend as intended, supporting the DS R1 requirements and kv events/metrics functionality. Users can still override via extra engine args if needed.

Note: This change makes the condition "backend" not in arg_map at line 378 effectively dead code since backend is now always present. Consider documenting this as a breaking change if users were relying on different default backend behavior.

Consider simplifying the validation logic at lines 378-384 since backend is now always set:

 # Only pytorch backend is supported for now to publish events and metrics.
-if "backend" not in arg_map:
-    arg_map["backend"] = "pytorch"
-elif arg_map["backend"] != "pytorch":
+if arg_map["backend"] != "pytorch":
     logging.error(
         "Only pytorch backend is supported for now to publish events and metrics."
     )
     sys.exit(1)

📜 Review details

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

📥 Commits

Reviewing files that changed from the base of the PR and between a673145 and 20131ef.

📒 Files selected for processing (1)

• launch/dynamo-run/src/subprocess/trtllm_inc.py (1 hunks)

⏰ Context from checks skipped due to timeout of 90000ms (4)

• GitHub Check: Build and Test - vllm
• GitHub Check: pre-merge-rust (lib/bindings/python)
• GitHub Check: pre-merge-rust (.)
• GitHub Check: pre-merge-rust (lib/runtime/examples)