[None][fix] type annotations in fuse_input_embeds #8976

ixlmar · 2025-11-06T14:24:11Z

Description

Ensures consistent usage of torch.IntTensor and torch.FloatTensor.

Note: It appears that those types are deprecated, but there appears to be no other PyTorch-native typing capability (cf. pytorch/pytorch#73359).

Test Coverage

No functional changes.

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

/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...

Provide a user friendly way for developers to interact with a Jenkins server.

Run /bot [-h|--help] to print this help message.

See details below for each supported subcommand.

run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental)]

Launch build/test pipelines. All previously running jobs will be killed.

--reuse-test (optional)pipeline-id (OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.

--disable-reuse-test (OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.

--disable-fail-fast (OPTIONAL) : Disable fail fast on build/tests/infra failures.

--skip-test (OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.

--stage-list "A10-PyTorch-1, xxx" (OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does NOT update GitHub check status.

--gpu-type "A30, H100_PCIe" (OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.

--test-backend "pytorch, cpp" (OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.

--only-multi-gpu-test (OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.

--disable-multi-gpu-test (OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.

--add-multi-gpu-test (OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.

--post-merge (OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.

--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".

--detailed-log (OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.

--debug (OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in the stage-list parameter to access the appropriate container environment. Note: Does NOT update GitHub check status.

For guidance on mapping tests to stage names, see docs/source/reference/ci-overview.md
and the scripts/test_to_stage_mapping.py helper.

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip testing for latest commit on pull request. --comment "Reason for skipping build/test" is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

reuse-pipeline

reuse-pipeline

Reuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

Summary by CodeRabbit

Refactor
- Strengthened type safety in multimodal embedding processing through enhanced type annotations to better reflect tensor types.
- Refined embedding tensor handling with explicit type casting to improve code reliability and maintainability.
- Updated type system integration for more robust internal tensor management.

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

ixlmar · 2025-11-06T14:24:32Z

/bot run --skip-test

coderabbitai · 2025-11-06T14:29:06Z

📝 Walkthrough

Walkthrough

The return type annotation of fuse_input_embeds is updated to reflect that the first element is an IntTensor instead of FloatTensor. An explicit cast to FloatTensor is added to the second return element, and cast is imported from the typing module.

Changes

Cohort / File(s)	Summary
Type annotation and import updates `tensorrt_llm/_torch/models/modeling_multimodal_utils.py`	Added `cast` import from `typing`. Updated `fuse_input_embeds` return type from `Tuple[Optional[torch.FloatTensor], Optional[torch.FloatTensor]]` to `Tuple[Optional[torch.IntTensor], Optional[torch.FloatTensor]]`. Updated return statement to explicitly cast the second element: `return (None, cast(torch.FloatTensor, input_embeds))`.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~5–10 minutes

Areas requiring attention:
- Verify that callers of fuse_input_embeds handle the new IntTensor return type for the first element correctly
- Confirm that the explicit cast to FloatTensor on the second element does not mask any actual type mismatches

Pre-merge checks and finishing touches

✅ Passed checks (3 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly and specifically describes the main change: fixing type annotations in the fuse_input_embeds function.
Description check	✅ Passed	The description explains the purpose (consistent type annotation usage) and notes the deprecated status of torch types, but lacks detail on test coverage and checklist items.
Docstring Coverage	✅ Passed	Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.

✨ Finishing touches

📝 Generate docstrings

🧪 Generate unit tests (beta)

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

📜 Recent review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between c73efe1 and 8752b6b.

📒 Files selected for processing (1)

tensorrt_llm/_torch/models/modeling_multimodal_utils.py (3 hunks)

🧰 Additional context used

📓 Path-based instructions (3)

**/*.{h,hpp,hh,hxx,cpp,cxx,cc,cu,cuh,py}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

Use only spaces, no tabs; indent with 4 spaces.

Files:

tensorrt_llm/_torch/models/modeling_multimodal_utils.py

**/*.py

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

**/*.py: Python code must target Python 3.8+.
Indent Python code with 4 spaces; do not use tabs.
Maintain module namespace when importing; prefer 'from package.subpackage import foo' then 'foo.SomeClass()' instead of importing the class directly.
Python filenames should be snake_case (e.g., some_file.py).
Python classes use PascalCase names.
Functions and methods use snake_case names.
Local variables use snake_case; prefix 'k' for variables that start with a number (e.g., k_99th_percentile).
Global variables use upper SNAKE_CASE prefixed with 'G' (e.g., G_MY_GLOBAL).
Constants use upper SNAKE_CASE (e.g., MY_CONSTANT).
Avoid shadowing variables from an outer scope.
Initialize all externally visible members of a class in the constructor.
Prefer docstrings for interfaces that may be used outside a file; comments for in-function or file-local interfaces.
Use Google-style docstrings for classes and functions (Sphinx-parsable).
Document attributes and variables inline so they render under the class/function docstring.
Avoid reflection when a simpler, explicit approach suffices (e.g., avoid dict(**locals()) patterns).
In try/except, catch the most specific exceptions possible.
For duck-typing try/except, keep the try body minimal and use else for the main logic.

Files:

tensorrt_llm/_torch/models/modeling_multimodal_utils.py

**/*.{cpp,cxx,cc,h,hpp,hh,hxx,cu,cuh,py}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

Prepend the NVIDIA Apache-2.0 copyright header with current year to the top of all source files (e.g., .cpp, .h, .cu, .py).

Files:

tensorrt_llm/_torch/models/modeling_multimodal_utils.py

🧠 Learnings (1)

📓 Common learnings

Learnt from: djns99
Repo: NVIDIA/TensorRT-LLM PR: 6915
File: cpp/tensorrt_llm/kernels/cutlass_kernels/moe_gemm/moe_kernels.cu:4010-4012
Timestamp: 2025-08-14T23:23:27.449Z
Learning: For MOE (Mixture of Experts) code reviews in TensorRT-LLM, avoid repeatedly suggesting finalize fusion validation checks and safety assertions. The user djns99 has indicated these suggestions are repetitive and unwanted across multiple MOE-related changes.

🧬 Code graph analysis (1)

tensorrt_llm/_torch/models/modeling_multimodal_utils.py (1)

tensorrt_llm/functional.py (2)

cast (474-478)

cast (876-919)

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)

GitHub Check: Pre-commit Check

🔇 Additional comments (2)

tensorrt_llm/_torch/models/modeling_multimodal_utils.py (2)

20-20: Import update looks good

Adding cast from typing lines up with the new usage below—no issues spotted.

295-341: Tuple typing now matches runtime behavior

Switching the first element of the return type to Optional[torch.IntTensor] and using typing.cast for the fused embeddings cleanly captures the two execution paths without altering runtime flow.

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

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

tensorrt-cicd · 2025-11-06T14:32:03Z

PR_Github #23749 [ run ] triggered by Bot. Commit: 8752b6b

tensorrt-cicd · 2025-11-06T16:33:31Z

PR_Github #23749 [ run ] completed with state SUCCESS. Commit: 8752b6b
/LLM/main/L0_MergeRequest_PR pipeline #17876 (Partly Tested) completed with status: 'SUCCESS'

ixlmar · 2025-11-06T16:45:39Z

/bot skip --comment "No functional changes"

ixlmar · 2025-11-06T16:45:57Z

/bot run

tensorrt-cicd · 2025-11-06T16:51:46Z

PR_Github #23756 [ run ] triggered by Bot. Commit: 8752b6b

tensorrt-cicd · 2025-11-06T16:52:35Z

PR_Github #23757 [ skip ] triggered by Bot. Commit: 8752b6b

tensorrt-cicd · 2025-11-06T16:52:37Z

PR_Github #23756 [ run ] completed with state ABORTED. Commit: 8752b6b

tensorrt-cicd · 2025-11-06T17:07:52Z

PR_Github #23757 [ skip ] completed with state SUCCESS. Commit: 8752b6b
Skipping testing for commit 8752b6b

yechank-nvidia · 2025-11-07T02:03:28Z

tensorrt_llm/_torch/models/modeling_multimodal_utils.py

    input_embeds[mm_token_indices, :] = mm_embed.to(dtype=input_embeds.dtype,
                                                    device=input_embeds.device)

-    return None, input_embeds


I'm not sure casting to FloatTensor may cause the forward fail. On other data types like Bfloat16, Float8

fix: type annotations in fuse_input_embeds

8752b6b

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

ixlmar requested a review from a team as a code owner November 6, 2025 14:24

ixlmar requested a review from yechank-nvidia November 6, 2025 14:24

yechank-nvidia reviewed Nov 7, 2025

View reviewed changes

[None][fix] type annotations in fuse_input_embeds #8976

Are you sure you want to change the base?

[None][fix] type annotations in fuse_input_embeds #8976

Uh oh!

Conversation

ixlmar commented Nov 6, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Test Coverage

PR Checklist

GitHub Bot Help

kill

skip

reuse-pipeline

Summary by CodeRabbit

Uh oh!

ixlmar commented Nov 6, 2025

Uh oh!

coderabbitai bot commented Nov 6, 2025

Walkthrough

Changes

Estimated code review effort

Pre-merge checks and finishing touches

Uh oh!

tensorrt-cicd commented Nov 6, 2025

Uh oh!

tensorrt-cicd commented Nov 6, 2025

Uh oh!

ixlmar commented Nov 6, 2025

Uh oh!

ixlmar commented Nov 6, 2025

Uh oh!

tensorrt-cicd commented Nov 6, 2025

Uh oh!

tensorrt-cicd commented Nov 6, 2025

Uh oh!

tensorrt-cicd commented Nov 6, 2025

Uh oh!

tensorrt-cicd commented Nov 6, 2025

Uh oh!

yechank-nvidia Nov 7, 2025

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

ixlmar commented Nov 6, 2025 •

edited

Loading