docs: Reference Deepseek R1 configs in TRTLLM README

[rmccorm4]

Overview:

Add explicit reference to Deepseek R1 configs for discoverability. Note these are just example configs for a particular configuration on GB200. They can be customized as needed for different parallelism strategies and hardware configurations, such as 8xH200 nodes.

Currently, these configs assume that each worker can fit on a single node (4xGB200, 8xH200, etc.), but support and steps for serving a single worker instance on multiple nodes (ex: 16xH100) will come in the future.

Summary by CodeRabbit

• Documentation
  • Updated the README to include an example for multi-node deployment.
  • Added instructions for deploying Deepseek R1 by using specific configuration files.
  • Provided a link to example configs for GB200 hardware and clarified customization options for other hardware or parallelism strategies.

[coderabbitai]

Walkthrough

The README file in the TensorRT LLM examples directory was updated to include instructions for deploying Deepseek R1 using specific configuration files. The update provides guidance on replacing default configs with Deepseek R1 configs and includes a reference link for GB200 hardware examples.

Changes

File(s)	Change Summary
examples/tensorrt_llm/README.md	Updated documentation to add Deepseek R1 multi-node deployment instructions and config references.

Poem

In README fields where configs dwell,
New Deepseek notes now clearly tell.
Swap your files, deploy with ease,
On GB200, do as you please.
A rabbit hops through docs anew—
Multi-node dreams now come true!
🐇✨

---

🪧 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)

examples/tensorrt_llm/README.md (1)

129-134: Consider a dedicated subsection for Deepseek R1 configs.
Extract these lines into a standalone "#### Deepseek R1 Example Configs" subheading (placed above the head/worker node steps) to improve readability and clearly separate R1-specific guidance from the multi-node instructions.

📜 Review details

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

📥 Commits

Reviewing files that changed from the base of the PR and between 2019a7d and fe958a8.

📒 Files selected for processing (1)

• examples/tensorrt_llm/README.md (1 hunks)

⏰ Context from checks skipped due to timeout of 90000ms (2)

• GitHub Check: Mirror Repository to GitLab
• GitHub Check: Build and Test - vllm

🔇 Additional comments (1)

examples/tensorrt_llm/README.md (1)

129-134: Verify Deepseek R1 config directory and files.
Ensure that the configs/deepseek_r1 path exists relative to this README and contains the referenced agg.yaml and disagg.yaml files. You may also consider using a leading ./ (e.g., ./configs/deepseek_r1/) to make it explicit that this is a directory link.

[rmccorm4]

Gitlab failure is unrelated to this PR, introduced by some other changes in new benchmarks/ directory - reached out to Rudy to help fix those failures separately.