[None][docs] fix multimodal serve client path, base64 util, and bench doc link

[imitater-dou]

Summary

• Point multimodal Chat API literalinclude at examples/serve/openai_chat_client_for_multimodal.py (ghost completion client path).
• Retarget base64 helper docs to tensorrt_llm.inputs.encode_base64_image.
• Fix performance-benchmarking doc link to run-benchmark-with-trtllm-serve.md.

Test plan

• Confirm examples/serve/openai_chat_client_for_multimodal.py exists and the old completion multimodal path does not.
• Confirm encode_base64_image is exported from tensorrt_llm.inputs.
• Confirm docs/source/commands/trtllm-serve/run-benchmark-with-trtllm-serve.md exists.
• Do not change enable_overlap_scheduler.

Dev Engineer Review

• Updated docs/source/commands/trtllm-serve/trtllm-serve.rst to use the correct multimodal Chat API example path.
• Updated the base64 helper reference to tensorrt_llm.inputs.encode_base64_image.
• Corrected the performance-benchmarking link and title.
• No source-code, API, configuration, scheduler, or runtime behavior changes.

QA Engineer Review

No test changes.

Per-File QA Perspective

• docs/source/commands/trtllm-serve/trtllm-serve.rst: Documentation-only changes. Verify that the referenced example file, tensorrt_llm.inputs.encode_base64_image export, and benchmarking document resolve correctly.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: d8ec2b60-270f-45f4-9430-3ba990bdcb76

📥 Commits

Reviewing files that changed from the base of the PR and between 96a25c4 and 3b1fb3f.

📒 Files selected for processing (1)

• docs/source/commands/trtllm-serve/trtllm-serve.rst

Included review availability: Your plan provides up to 12 included reviews per hour; 7 remain after this review.

---

Walkthrough

The serving documentation updates the multimodal Chat API example, image base64 encoding utility reference, and performance benchmarking link.

Changes

Serving documentation

Layer / File(s)	Summary
Update serving documentation references docs/source/commands/trtllm-serve/trtllm-serve.rst	The multimodal example uses the Chat API and its client example. The image encoding reference uses tensorrt_llm.inputs.encode_base64_image. The benchmarking link points to the updated guide.

Priority: ⬇️ Low

Estimated code review effort: 1 (Trivial) | ~2 minutes

Merge Risk: ⚪ Minimal · up to 3b1fb

This change updates serving documentation to point users to the current multimodal Chat API example, base64 image helper, and benchmarking guide. The referenced targets are present and aligned with the documented workflows, with no remaining merge-readiness risk.

Suggested reviewers: bowenfu

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title follows the required [None][type] format and clearly summarizes the documentation fixes for the multimodal client path, base64 utility, and benchmark link.
Description check	✅ Passed	The description explains the documentation changes and provides a relevant test plan. It does not include the template checklist, but the required change and validation details are sufficiently covere…
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Analyzed 0 functions across 0…
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

_{Comment @coderabbitai help to get the list of available commands.}

[brnguyen2]

Approving — the comments below are optional touch-ups, not blockers.

Verified all three claims against the tree: examples/serve/openai_chat_client_for_multimodal.py exists (no completion-variant multimodal client), encode_base64_image is exported from tensorrt_llm/inputs/__init__.py and defined in inputs/utils.py:272, and docs/source/commands/trtllm-serve/run-benchmark-with-trtllm-serve.md exists. Fixes are correct.

One thing to fix before merge (inline). Optionally, since the benchmark doc is in the same docs tree, :doc: (:doc:`run-benchmark-with-trtllm-serve`) would be a versioned in-tree link instead of a hardcoded main blob URL.

[brnguyen2]

This drops the trailing newline at EOF. .pre-commit-config.yaml enables end-of-file-fixer with no .rst exclusion, so this will be modified by the hook (and fail the pre-commit CI check). Re-add the newline, or run pre-commit run --files docs/source/commands/trtllm-serve/trtllm-serve.rst and re-stage.