[None][fix] Remove obsolete GPT-OSS two-model Eagle3 tests

[achartier]

Dev Engineer Review

• Removed two obsolete GPT-OSS two-model Eagle3 tests.
• The removal matches the disabled two-model speculative decoding path.
• No production code, configuration, or test-list files changed.
• Existing one-model Eagle3 and KV-cache V2 coverage remains.

QA Engineer Review

• Removed:
  • test_gpt_oss_two_model_eagle3_falls_back_to_v1()
  • test_gpt_oss_explicit_v2_rejects_two_model_eagle3()
• No tests/integration/test_lists/ files changed.
• The removed tests are not covered by test-list entries. Existing supported GPT-OSS KV-cache behavior remains covered.
• Verdict: sufficient

Description

Two GPT-OSS KV-cache tests still exercised the deprecated two-model Eagle3 path after two-model speculative decoding was disabled. Since eagle3_one_model=False is now ignored and normalized to the supported one-model configuration, the old V1 fallback and explicit-V2 rejection assertions no longer represent reachable behavior.

Remove the obsolete two-model tests. Existing tests continue to cover GPT-OSS KV-cache V2 selection, explicit user settings, and supported one-model Eagle3 behavior.

Test Coverage

N/A - test removal only

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.

[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: f2590361-8597-4f56-8dea-113b40728571

📥 Commits

Reviewing files that changed from the base of the PR and between 148f1f2 and 0871216.

📒 Files selected for processing (1)

• tests/unittest/_torch/modeling/test_modeling_gpt_oss.py

💤 Files with no reviewable changes (1)

• tests/unittest/_torch/modeling/test_modeling_gpt_oss.py

---

Walkthrough

The change removes two GPT-OSS tests for two-model Eagle3 KV cache manager behavior. One-model Eagle3 V2 coverage remains.

Changes

GPT-OSS Eagle3 test cleanup

Layer / File(s)	Summary
Remove obsolete fallback assertions tests/unittest/_torch/modeling/test_modeling_gpt_oss.py	Removes tests for V1 fallback and explicit V2 rejection in two-model Eagle3 configurations. One-model Eagle3 V2 coverage remains.

Estimated code review effort: 1 (Trivial) | ~3 minutes

Mergeability Score: ⚪ Minimal · up to 08712

This change removes obsolete tests without altering production behavior, and no actionable merge-blocking risk remains beyond normal checks and review.

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly and concisely describes the removal of obsolete GPT-OSS two-model Eagle3 tests.
Description check	✅ Passed	The description explains the reason for the test removals, identifies affected behavior, and documents remaining test coverage.
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.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[achartier]

/bot run

[tensorrt-cicd]

PR_Github #65776 [ run ] triggered by Bot. Commit: 0871216 Link to invocation

[tensorrt-cicd]

PR_Github #65776 [ run ] completed with state SUCCESS. Commit: 0871216
/LLM/main/L0_MergeRequest_PR pipeline #53486 completed with status: 'SUCCESS'

CI Report

Link to invocation