chore: remove draft_model_engine from init parameter list of PyExecutor #6325

QiJune · 2025-07-24T06:13:28Z

Summary by CodeRabbit

Refactor
- Centralized draft model engine handling through the drafter component to improve internal consistency without affecting user experience.

coderabbitai · 2025-07-24T06:13:35Z

📝 Walkthrough

Walkthrough

This change removes the explicit draft_model_engine parameter and attribute from the PyExecutor class and related functions. All handling of the draft model engine is now unified under the drafter abstraction, eliminating direct references and arguments for draft_model_engine throughout the codebase.

Changes

File(s)	Change Summary
Utility function update `tensorrt_llm/_torch/pyexecutor/_util.py`	Removed `draft_model_engine` parameter from `create_py_executor_instance` signature and all internal references.
PyExecutor class update `tensorrt_llm/_torch/pyexecutor/py_executor.py`	Removed `draft_model_engine` parameter/attribute from `PyExecutor`; now accesses via `drafter` if present.
Executor creation update `tensorrt_llm/_torch/pyexecutor/py_executor_creator.py`	Removed passing of `draft_model_engine` in calls to `create_py_executor_instance` within `create_py_executor`.

Sequence Diagram(s)

sequenceDiagram
    participant Caller
    participant create_py_executor_instance
    participant PyExecutor
    participant Drafter

    Caller->>create_py_executor_instance: call (without draft_model_engine)
    create_py_executor_instance->>PyExecutor: instantiate (drafter=..., no draft_model_engine)
    PyExecutor->>Drafter: use drafter.draft_model_engine if drafter exists

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Possibly related PRs

[TRTLLM-6352][feat] Migrate EAGLE3 and draft/target speculation to Drafter #6007: Refactors draft model handling into the Drafter class and removes draft model engine usage from PyExecutor methods, directly related to this unification.

Suggested reviewers

pcastonguay
HuiGao-NV
leslie-fang25

Note

⚡️ Unit Test Generation is now available in beta!

Learn more here, or try it out under "Finishing Touches" below.

📜 Recent review details

Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 60e4015 and 447d401.

📒 Files selected for processing (1)

tensorrt_llm/_torch/pyexecutor/py_executor.py (1 hunks)

🚧 Files skipped from review as they are similar to previous changes (1)

tensorrt_llm/_torch/pyexecutor/py_executor.py

✨ Finishing Touches

📝 Generate Docstrings

🧪 Generate unit tests

Create PR with unit tests
Post copyable unit tests in a comment

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

Review comments: Directly reply to a review comment made by CodeRabbit. Example:
- I pushed a fix in commit <commit_id>, please review it.
- Explain this complex logic.
- Open a follow-up GitHub issue for this discussion.
Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
- @coderabbitai explain this code block.
- @coderabbitai modularize this function.
PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
- @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
- @coderabbitai read src/utils.ts and explain its main purpose.
- @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
- @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

@coderabbitai pause to pause the reviews on a PR.
@coderabbitai resume to resume the paused reviews.
@coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
@coderabbitai full review to do a full review from scratch and review all the files again.
@coderabbitai summary to regenerate the summary of the PR.
@coderabbitai generate docstrings to generate docstrings for this PR.
@coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
@coderabbitai generate unit tests to generate unit tests for this PR.
@coderabbitai resolve resolve all the CodeRabbit review comments.
@coderabbitai configuration to show the current CodeRabbit configuration for the repository.
@coderabbitai help to get help.

Other keywords and placeholders

Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
Add @coderabbitai or @coderabbitai title anywhere in the PR title to generate the title automatically.

Documentation and Community

Visit our Documentation for detailed information on how to use CodeRabbit.
Join our Discord Community to get help, request features, and share feedback.
Follow us on X/Twitter for updates and announcements.

QiJune · 2025-07-24T06:14:03Z

/bot run

tensorrt-cicd · 2025-07-24T06:19:12Z

PR_Github #12814 [ run ] triggered by Bot

tensorrt-cicd · 2025-07-24T07:50:27Z

PR_Github #12814 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #9548 completed with status: 'FAILURE'

Signed-off-by: junq <[email protected]>

QiJune · 2025-07-24T09:59:17Z

/bot run

tensorrt-cicd · 2025-07-24T10:07:07Z

PR_Github #12842 [ run ] triggered by Bot

tensorrt-cicd · 2025-07-24T10:07:11Z

PR_Github #12842 [ run ] completed with state FAILURE

QiJune · 2025-07-24T12:54:22Z

/bot run

tensorrt-cicd · 2025-07-24T12:59:17Z

PR_Github #12853 [ run ] triggered by Bot

tensorrt-cicd · 2025-07-24T12:59:21Z

PR_Github #12853 [ run ] completed with state FAILURE

QiJune · 2025-07-24T13:08:01Z

/bot run

tensorrt-cicd · 2025-07-24T13:13:06Z

PR_Github #12857 [ run ] triggered by Bot

tensorrt-cicd · 2025-07-24T13:13:10Z

PR_Github #12857 [ run ] completed with state FAILURE

tensorrt_llm/_torch/pyexecutor/py_executor.py

Signed-off-by: junq <[email protected]>

QiJune · 2025-07-25T01:18:11Z

/bot run

tensorrt-cicd · 2025-07-25T01:30:05Z

PR_Github #12917 [ run ] triggered by Bot

tensorrt-cicd · 2025-07-25T05:09:01Z

PR_Github #12917 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #9631 completed with status: 'FAILURE'

tensorrt-cicd · 2025-07-26T04:57:03Z

PR_Github #13062 [ run ] triggered by Bot

tensorrt-cicd · 2025-07-26T05:08:19Z

PR_Github #13062 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #9761 completed with status: 'FAILURE'

QiJune · 2025-07-28T00:49:18Z

/bot run

tensorrt-cicd · 2025-07-28T00:54:18Z

PR_Github #13119 [ run ] triggered by Bot

tensorrt-cicd · 2025-07-28T04:02:15Z

PR_Github #13119 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #9817 completed with status: 'FAILURE'

QiJune · 2025-07-28T05:24:39Z

/bot run

QiJune · 2025-07-29T00:28:16Z

/bot run

tensorrt-cicd · 2025-07-29T00:33:28Z

PR_Github #13252 [ run ] triggered by Bot

tensorrt-cicd · 2025-07-29T00:53:32Z

PR_Github #13252 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #9896 completed with status: 'FAILURE'

QiJune · 2025-07-29T08:25:53Z

/bot run

tensorrt-cicd · 2025-07-29T08:30:55Z

PR_Github #13331 [ run ] triggered by Bot

tensorrt-cicd · 2025-07-29T10:35:28Z

PR_Github #13331 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #9964 completed with status: 'FAILURE'

QiJune · 2025-07-29T11:53:37Z

/bot run

tensorrt-cicd · 2025-07-29T11:58:47Z

PR_Github #13365 [ run ] triggered by Bot

tensorrt-cicd · 2025-07-30T01:23:56Z

PR_Github #13365 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #9995 completed with status: 'FAILURE'

QiJune · 2025-07-30T03:21:41Z

/bot run

tensorrt-cicd · 2025-07-30T03:27:15Z

PR_Github #13467 [ run ] triggered by Bot

tensorrt-cicd · 2025-07-30T07:31:47Z

PR_Github #13467 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #10081 completed with status: 'SUCCESS'

…or (NVIDIA#6325) Signed-off-by: junq <[email protected]> Signed-off-by: Lanyu Liao <[email protected]>

…or (NVIDIA#6325) Signed-off-by: junq <[email protected]>

remove draft_model_engine from init parameter list of PyExecutor

eb3cf0c

Signed-off-by: junq <[email protected]>

QiJune requested a review from a team as a code owner July 24, 2025 06:13

QiJune requested a review from mikeiovine July 24, 2025 06:13

coderabbitai bot requested review from HuiGao-NV and suyoggupta July 24, 2025 06:13

fix ci

eea4d94

Signed-off-by: junq <[email protected]>

coderabbitai bot requested a review from nv-guomingz July 24, 2025 09:58

Merge branch 'main' into clean_drafter

e67154a

Merge branch 'main' into clean_drafter

c4e4896

mikeiovine reviewed Jul 24, 2025

View reviewed changes

tensorrt_llm/_torch/pyexecutor/py_executor.py Outdated Show resolved Hide resolved

QiJune added 2 commits July 25, 2025 09:11

Merge branch 'main' into clean_drafter

8fae9be

fix comments

46766b9

Signed-off-by: junq <[email protected]>

QiJune requested a review from leslie-fang25 July 25, 2025 02:33

leslie-fang25 approved these changes Jul 25, 2025

View reviewed changes

nv-guomingz approved these changes Jul 26, 2025

View reviewed changes

Merge branch 'main' into clean_drafter

22e0a6a

Merge branch 'main' into clean_drafter

60e4015

coderabbitai bot requested a review from nv-guomingz July 29, 2025 00:26

Merge branch 'main' into clean_drafter

447d401

coderabbitai bot requested review from leslie-fang25 and pcastonguay July 29, 2025 08:25

leslie-fang25 approved these changes Jul 30, 2025

View reviewed changes

QiJune merged commit 2fe9cc0 into NVIDIA:main Jul 30, 2025
3 checks passed

lancelly pushed a commit to lancelly/TensorRT-LLM that referenced this pull request Aug 6, 2025

chore: remove draft_model_engine from init parameter list of PyExecut…

132f1ae

…or (NVIDIA#6325) Signed-off-by: junq <[email protected]> Signed-off-by: Lanyu Liao <[email protected]>

jain-ria pushed a commit to jain-ria/TensorRT-LLM that referenced this pull request Aug 7, 2025

chore: remove draft_model_engine from init parameter list of PyExecut…

24b60c9

…or (NVIDIA#6325) Signed-off-by: junq <[email protected]>

coderabbitai bot mentioned this pull request Aug 22, 2025

[TRTLLM-7353][feat] Implement capturable drafting loops for speculation #7100

Merged

chore: remove draft_model_engine from init parameter list of PyExecutor #6325

chore: remove draft_model_engine from init parameter list of PyExecutor #6325

Uh oh!

Conversation

QiJune commented Jul 24, 2025 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Uh oh!

coderabbitai bot commented Jul 24, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Sequence Diagram(s)

Estimated code review effort

Possibly related PRs

Suggested reviewers

Chat

Support

CodeRabbit Commands (Invoked using PR comments)

Other keywords and placeholders

Documentation and Community

Uh oh!

QiJune commented Jul 24, 2025

Uh oh!

tensorrt-cicd commented Jul 24, 2025

Uh oh!

tensorrt-cicd commented Jul 24, 2025

Uh oh!

QiJune commented Jul 24, 2025

Uh oh!

tensorrt-cicd commented Jul 24, 2025

Uh oh!

tensorrt-cicd commented Jul 24, 2025

Uh oh!

QiJune commented Jul 24, 2025

Uh oh!

tensorrt-cicd commented Jul 24, 2025

Uh oh!

tensorrt-cicd commented Jul 24, 2025

Uh oh!

QiJune commented Jul 24, 2025

Uh oh!

tensorrt-cicd commented Jul 24, 2025

Uh oh!

tensorrt-cicd commented Jul 24, 2025

Uh oh!

Uh oh!

QiJune commented Jul 25, 2025

Uh oh!

tensorrt-cicd commented Jul 25, 2025

Uh oh!

tensorrt-cicd commented Jul 25, 2025

Uh oh!

tensorrt-cicd commented Jul 26, 2025

Uh oh!

tensorrt-cicd commented Jul 26, 2025

Uh oh!

QiJune commented Jul 28, 2025

Uh oh!

tensorrt-cicd commented Jul 28, 2025

Uh oh!

tensorrt-cicd commented Jul 28, 2025

Uh oh!

QiJune commented Jul 28, 2025

Uh oh!

QiJune commented Jul 29, 2025

Uh oh!

tensorrt-cicd commented Jul 29, 2025

Uh oh!

tensorrt-cicd commented Jul 29, 2025

Uh oh!

QiJune commented Jul 29, 2025

Uh oh!

tensorrt-cicd commented Jul 29, 2025

Uh oh!

tensorrt-cicd commented Jul 29, 2025

Uh oh!

QiJune commented Jul 29, 2025

Uh oh!

tensorrt-cicd commented Jul 29, 2025

QiJune commented Jul 24, 2025 •

edited by coderabbitai bot

Loading

coderabbitai bot commented Jul 24, 2025 •

edited

Loading