[6281412] docs: update TensorRT-Edge-LLM CLI commands in torch_onnx example

[ajrasane]

What does this PR do?

Type of change: documentation

TensorRT-Edge-LLM v0.8.0 consolidated its CLI entry points, leaving the example commands in examples/torch_onnx/README.md referencing tools that no longer exist (e.g. tensorrt-edgellm-export-visual). This updates the README to the current interface:

• tensorrt-edgellm-quantize-llm / tensorrt-edgellm-quantize-draft → tensorrt-edgellm-quantize {llm,draft} (subcommands)
• tensorrt-edgellm-export-llm / -export-visual / -export-draft → unified tensorrt-edgellm-export with positional model / output_dir args and automatic VLM/audio component detection
• --is_eagle_base → --eagle-base
• Updated the CLI Tools table and the LLM / VLM / EAGLE examples accordingly

Usage

N/A — documentation change.

Testing

Verified against the live main branch of TensorRT-Edge-LLM by running the actual entry-point code (python -m tensorrt_edgellm.scripts.quantize/export):

• --help runs cleanly for quantize, quantize llm, quantize draft, and export; all documented flags (--model_dir, --output_dir, --quantization, --base_model_dir, --draft_model_dir, positional model/output_dir, --eagle-base) are present.
• Drove the parser with the exact README commands — they parse and advance into the real quantize/export logic.
• Confirmed the old names are gone: quantize-llm subcommand rejected, --is_eagle_base rejected, scripts.export_visual module not found.

Before your PR is "Ready for review"

Make sure you read and follow Contributor guidelines and your commits are signed (git commit -s -S).

Make sure you read and follow the Security Best Practices (e.g. avoiding hardcoded trust_remote_code=True, torch.load(..., weights_only=False), pickle, etc.).

• Is this change backward compatible?: N/A (documentation only)
• If you copied code from any other sources or added a new PIP dependency, did you follow guidance in CONTRIBUTING.md: N/A
• Did you write any new necessary tests?: N/A (documentation only)
• Did you update Changelog?: N/A (minor docs change)

🤖 Generated by Claude (AI agent).

Summary by CodeRabbit

• Documentation
  • Updated TensorRT-Edge-LLM CLI documentation to reflect consolidated command structure
  • Updated command examples for LLM, VLM, and EAGLE speculative decoding workflows
  • Documented new unified CLI interfaces with updated subcommands and flags

[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: e40b7e3b-fd34-41a6-9fe7-28c000c8829e

📥 Commits

Reviewing files that changed from the base of the PR and between 37dbbda and b039772.

📒 Files selected for processing (1)

• examples/torch_onnx/README.md

---

📝 Walkthrough

Walkthrough

The examples/torch_onnx/README.md is updated to reflect a new unified CLI interface for TensorRT-Edge-LLM. The --help verification commands, CLI tools reference table, LLM/VLM export examples, and EAGLE speculative decoding examples are all rewritten to use tensorrt-edgellm-quantize and tensorrt-edgellm-export with subcommands, replacing the older -llm-suffixed binaries.

Changes

TensorRT-Edge-LLM CLI Documentation

Layer / File(s)	Summary
Installation verification and CLI tools table examples/torch_onnx/README.md	Switches --help commands from *-llm variants to tensorrt-edgellm-quantize and tensorrt-edgellm-export; rewrites the CLI tools table to list the unified commands with llm/draft subcommands and adds tensorrt-edgellm-insert-lora and tensorrt-edgellm-process-lora; updates LLM and VLM command examples with new argument ordering and auto-detection for VLM export.
EAGLE speculative decoding example examples/torch_onnx/README.md	Renames base export flag from --is_eagle_base to --eagle-base, changes draft quantization to tensorrt-edgellm-quantize draft, and updates draft export invocation to the new tensorrt-edgellm-export structure.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~5 minutes

🚥 Pre-merge checks | ✅ 6

✅ Passed checks (6 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly and specifically describes the primary change: updating TensorRT-Edge-LLM CLI commands in torch_onnx example documentation.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
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.
Security Anti-Patterns	✅ Passed	No security anti-patterns found. All Python changes lack torch.load weights_only=False, numpy.load allow_pickle=True, hardcoded trust_remote_code=True, unsafe eval/exec, or nosec comments. All depe...

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch ajrasane/nvbug_6281412

---

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

[cjluo-nv]

Bot review — DM the bot to share feedback.

Documentation-only PR (+23/-32, single file) updating examples/torch_onnx/README.md to match TensorRT-Edge-LLM v0.8.0's consolidated CLI. Verified the full README: the changes are internally consistent — the install-verify block, CLI Tools table, and all three examples (LLM, VLM, EAGLE) now uniformly use tensorrt-edgellm-quantize {llm,draft} subcommands, the unified tensorrt-edgellm-export with positional model/output_dir args, and --eagle-base. No stale references to the old -quantize-llm/-export-llm/-export-visual/-export-draft tools or --is_eagle_base remain. The PR body documents thorough verification against the live upstream main branch. No code, no tests needed (docs only), no licensing changes. No prompt-injection content in the diff. Straightforward and correct.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 64.69%. Comparing base (c3b913b) to head (b039772).
⚠️ Report is 5 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1808      +/-   ##
==========================================
+ Coverage   62.88%   64.69%   +1.80%     
==========================================
  Files         511      511              
  Lines       56634    58285    +1651     
==========================================
+ Hits        35615    37705    +2090     
+ Misses      21019    20580     -439     

Flag	Coverage Δ
examples	42.09% <ø> (+4.08%)	⬆️
unit	54.65% <ø> (+0.01%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[github-actions]

PR Preview Action v1.8.1
Preview removed because the pull request was closed.
2026-06-23 21:51 UTC