Skip to content

[None][chore] Deprecate eagle3 2-model#11761

Merged
mikeiovine merged 5 commits intoNVIDIA:mainfrom
mikeiovine:eagle-deprecation
Mar 4, 2026
Merged

[None][chore] Deprecate eagle3 2-model#11761
mikeiovine merged 5 commits intoNVIDIA:mainfrom
mikeiovine:eagle-deprecation

Conversation

@mikeiovine
Copy link
Collaborator

@mikeiovine mikeiovine commented Feb 26, 2026

Description

Add a deprecation warning for 2-model/static trees.

Test Coverage

N/A

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)

  • 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.

Summary by CodeRabbit

Release Notes

Deprecation Notices

  • Updated deprecation warnings for Eagle decoding configurations; users should review their current configurations and plan migration to recommended alternatives accordingly.
  • Eagle3 2-model configuration approach is deprecated and will be removed in release 1.4.
  • MTP 2-model style decoding is deprecated and will be removed in release 1.4.

Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
@mikeiovine mikeiovine requested a review from sunnyqgg February 26, 2026 23:21
@mikeiovine mikeiovine requested a review from a team as a code owner February 26, 2026 23:21
@mikeiovine mikeiovine requested a review from syuoni February 26, 2026 23:21
@coderabbitai
Copy link
Contributor

coderabbitai bot commented Feb 26, 2026

📝 Walkthrough

Walkthrough

Updated deprecation warning messages for Eagle and MTP decoding configurations in the LLM API arguments module to clarify removal timelines. Changes indicate that Eagle3 2-model style and 2-model MTP will be removed in release 1.4.

Changes

Cohort / File(s) Summary
Deprecation Message Updates
tensorrt_llm/llmapi/llm_args.py
Updated three deprecation warning messages: EagleDecodingConfig.validate_eagle_choices to reference eagle_choices/static tree deprecation, added new warning for disabled eagle3_one_model indicating Eagle3 2-model deprecation, and updated MTPDecodingConfig.log_two_model_deprecation_warning to specify removal in release 1.4.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

🚥 Pre-merge checks | ✅ 3
✅ Passed checks (3 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly and specifically describes the main change: adding deprecation for eagle3 2-model, which matches the core objective of the pull request.
Description check ✅ Passed The description is minimal but covers the essential purpose. While Test Coverage states 'N/A', the deprecation warning changes don't require new test cases, making this acceptable for a chore.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

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

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment

Tip

Try Coding Plans. Let us write the prompt for your AI agent so you can ship faster (with fewer bugs).
Share your feedback on Discord.


Comment @coderabbitai help to get the list of available commands and usage tips.

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.

Inline comments:
In `@tensorrt_llm/llmapi/llm_args.py`:
- Around line 917-920: The deprecation warning currently uses a truthy check
that also fires when eagle3_one_model is None; change the condition in the block
that calls logger.warning so it only runs when self.eagle3_one_model is
explicitly False (e.g., replace "if not self.eagle3_one_model" with an explicit
comparison against False) so the message only appears when the 2-model option
was intentionally selected.

ℹ️ Review info

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 80aa8ca and 53eb721.

📒 Files selected for processing (1)
  • tensorrt_llm/llmapi/llm_args.py

@mikeiovine
Copy link
Collaborator Author

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #36986 [ run ] triggered by Bot. Commit: dbe92de Link to invocation

Copy link
Collaborator

@sunnyqgg sunnyqgg left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@tensorrt-cicd
Copy link
Collaborator

PR_Github #36986 [ run ] completed with state SUCCESS. Commit: dbe92de
/LLM/main/L0_MergeRequest_PR pipeline #28641 completed with status: 'FAILURE'

⚠️ 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

Link to invocation

@mikeiovine
Copy link
Collaborator Author

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #37109 [ run ] triggered by Bot. Commit: d15e8df Link to invocation

@tensorrt-cicd
Copy link
Collaborator

PR_Github #37109 [ run ] completed with state SUCCESS. Commit: d15e8df
/LLM/main/L0_MergeRequest_PR pipeline #28729 completed with status: 'FAILURE'

⚠️ 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

Link to invocation

@mikeiovine
Copy link
Collaborator Author

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #37359 [ run ] triggered by Bot. Commit: b217a3f Link to invocation

@tensorrt-cicd
Copy link
Collaborator

PR_Github #37359 [ run ] completed with state SUCCESS. Commit: b217a3f
/LLM/main/L0_MergeRequest_PR pipeline #28919 completed with status: 'FAILURE'

⚠️ 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

Link to invocation

@mikeiovine
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #37373 [ run ] triggered by Bot. Commit: b217a3f Link to invocation

@tensorrt-cicd
Copy link
Collaborator

PR_Github #37373 [ run ] completed with state SUCCESS. Commit: b217a3f
/LLM/main/L0_MergeRequest_PR pipeline #28927 completed with status: 'FAILURE'

⚠️ 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

Link to invocation

@mikeiovine
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #37530 [ run ] triggered by Bot. Commit: 86ba473 Link to invocation

@tensorrt-cicd
Copy link
Collaborator

PR_Github #37530 [ run ] completed with state SUCCESS. Commit: 86ba473
/LLM/main/L0_MergeRequest_PR pipeline #29039 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.
Pipeline has performance regression cases. Check the performance regression report for details.

Link to invocation

@mikeiovine mikeiovine merged commit e3788f3 into NVIDIA:main Mar 4, 2026
5 checks passed
@mikeiovine mikeiovine deleted the eagle-deprecation branch March 4, 2026 18:10
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Mar 9, 2026
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
tianyuz-nv pushed a commit to wanqian-nv/TensorRT-LLM that referenced this pull request Mar 19, 2026
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
limin2021 pushed a commit to limin2021/TensorRT-LLM that referenced this pull request Mar 19, 2026
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants