[None][docs] drop ghost --backend tensorrt from trtllm-eval docs

[imitater-dou]

Summary

• trtllm-eval Click --backend Choice is only ["pytorch"] and always constructs PyTorchLLM.
• Docs still told users to pass --backend tensorrt and that --model accepts pre-built TensorRT engines (with --tokenizer). Both are stale after the TensorRT engine backend removal (see docs/source/legacy/tensorrt-backend-removal.md).
• Drop those claims from docs/source/commands/trtllm-eval.rst and examples/trtllm-eval/README.md. Keep HF-or-local-checkpoint / PyTorch-only wording.

Repro

Upstream tensorrt_llm/commands/eval.py:

--backend type=click.Choice(["pytorch"])  # only
# non-pytorch → BadParameter

Test plan

• Confirmed Choice(["pytorch"]) on HEAD adfc41e
• grep both files: no --backend tensorrt, no pre-built TensorRT engines
• Diff limited to the two doc files

Signed-off-by: ADou ikun3.1415927@gmail.com

Dev Engineer Review

The documentation now states that trtllm-eval supports only the pytorch backend. It removes outdated guidance for TensorRT backends and pre-built TensorRT engines. No source code, API, configuration, or runtime behavior changed.

QA Engineer Review

No test changes.

Per-File QA Perspective

• docs/source/commands/trtllm-eval.rst: Documentation-only change. Verify that the supported backend guidance matches current trtllm-eval behavior.
• examples/trtllm-eval/README.md: Documentation-only change. Verify that HF/local-checkpoint and PyTorch-only usage remains accurate.

[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: 56463d60-e198-4aaa-9d4f-bf6389bbffa4

📥 Commits

Reviewing files that changed from the base of the PR and between eca1022 and 03e6f34.

📒 Files selected for processing (2)

• docs/source/commands/trtllm-eval.rst
• examples/trtllm-eval/README.md

Included review availability: Your plan provides up to 12 included reviews per hour; 10 remain after this review.

---

Walkthrough

The documentation now states that trtllm-eval supports only the PyTorch backend. TensorRT backend selection and pre-built TensorRT engine paths are no longer documented.

Changes

trtllm-eval documentation

Layer / File(s)	Summary
Update backend support documentation docs/source/commands/trtllm-eval.rst, examples/trtllm-eval/README.md	The command reference and example README limit trtllm-eval to the PyTorch backend and remove TensorRT engine guidance.

Priority: ⬇️ Low

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

Merge Risk: ⚪ Minimal · up to 03e6f

The documentation now consistently removes unsupported TensorRT backend and engine guidance for trtllm-eval while retaining the supported PyTorch workflow. No current merge-readiness risk remains.

Suggested reviewers: bowenfu

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly identifies the documentation change and the removal of the obsolete TensorRT backend option from trtllm-eval.
Description check	✅ Passed	The description explains the stale documentation, the current PyTorch-only behavior, the affected files, and the verification steps. It does not reproduce the template headings or PR checklist, but it…
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.}