[None][fix] Remove unreachable model path from MTPDraftModel

[nv-guomingz]

Summary by CodeRabbit

• Bug Fixes
  • Adjusted model selection so a previously special-cased configuration now follows the standard compatibility checks.
  • Unsupported models are now more reliably routed to the appropriate fallback/error path instead of being handled incorrectly.

Description

Test Coverage

PR Checklist

Please review the following before submitting your PR:

• PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.

• PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.

• Test cases are provided for new code paths (see test instructions)

• If PR introduces API changes, an appropriate PR label is added - either api-compatible or api-breaking. For api-breaking, include BREAKING in the PR title.

• Any new dependencies have been scanned for license and vulnerabilities

• CODEOWNERS updated if ownership changes

• Documentation updated as needed

• Update tava architecture diagram if there is a significant design change in PR.

• The reviewers assigned automatically/manually are appropriate for the PR.

• Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

To see a list of available CI bot commands, please comment /bot help.

[nv-guomingz]

/bot run --disable-fail-fast

[coderabbitai]

📝 Walkthrough

Walkthrough

Removes the exaone_moe branch from the model_type dispatch in MTPDraftModel.__init__, deleting the import and instantiation of ExaoneMoeMTP. The exaone_moe model type now falls through to subsequent cases or raises a ValueError.

Remove exaone_moe MTP dispatch

Layer / File(s)	Summary
Remove exaone_moe branch in MTPDraftModel tensorrt_llm/_torch/models/modeling_speculative.py	Deletes the model_type in ["exaone_moe"] match case and ExaoneMoeMTP instantiation from MTPDraftModel.__init__.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description keeps the template but leaves Description and Test Coverage empty.	Add a brief problem/solution summary and the tests covering this change; the checklist can stay as-is.

✅ Passed checks (4 passed)

Check name	Status	Explanation
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.
Title check	✅ Passed	The title matches the PR's main change: removing an unreachable MTPDraftModel code path.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[tensorrt-cicd]

PR_Github #56393 [ run ] triggered by Bot. Commit: 416ef9e Link to invocation

[nv-guomingz]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #56426 [ run ] triggered by Bot. Commit: 6f9f909 Link to invocation

[tensorrt-cicd]

PR_Github #56393 [ run ] completed with state ABORTED. Commit: 416ef9e

Link to invocation

[tensorrt-cicd]

PR_Github #56426 [ run ] completed with state FAILURE. Commit: 6f9f909
/LLM/main/L0_MergeRequest_PR pipeline #45269 completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

• Please check the failed tests and fix your PR
• If you cannot view the failures, ask the CI triggerer to share details
• Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

[nv-guomingz]

/bot run --disable-fail-fast

[sunnyqgg]

LGTM

[nv-guomingz]

/bot run --disable-fail-fast

[nv-guomingz]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #57141 [ run ] triggered by Bot. Commit: 18b00aa Link to invocation

[tensorrt-cicd]

PR_Github #57141 [ run ] completed with state FAILURE. Commit: 18b00aa
/LLM/main/L0_MergeRequest_PR pipeline #45923 completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

• Please check the failed tests and fix your PR
• If you cannot view the failures, ask the CI triggerer to share details
• Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

[nv-guomingz]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #57474 [ run ] triggered by Bot. Commit: 18b00aa Link to invocation

[tensorrt-cicd]

PR_Github #57474 [ run ] completed with state SUCCESS. Commit: 18b00aa
/LLM/main/L0_MergeRequest_PR pipeline #46209 completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

• Please check the failed tests and fix your PR
• If you cannot view the failures, ask the CI triggerer to share details
• Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

[nv-guomingz]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #57524 [ run ] triggered by Bot. Commit: 18b00aa Link to invocation

[tensorrt-cicd]

PR_Github #57524 [ run ] completed with state SUCCESS. Commit: 18b00aa
/LLM/main/L0_MergeRequest_PR pipeline #46254 completed with status: 'SUCCESS'

CI Report

Link to invocation