[None][fix] Fix get_num_tokens_per_image for nano-v2-vlm #8425
Conversation
Wanli-Jiang
requested review from
jaedeok-nvidia,
omera-nv and
yechank-nvidia
📝 WalkthroughWalkthroughThe change updates the aspect ratio selection algorithm in the image tiling logic for NanoV2VLM. It replaces factor-based selection with absolute difference-based selection between actual and target aspect ratios, introducing a tie-break condition that prefers larger areas subject to a threshold. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes The change involves a localized but non-trivial algorithm modification. Review requires understanding the original factor-based selection logic, the new ratio difference approach, and the tie-break heuristic to verify correctness and confirm it produces expected aspect ratio selections for typical image dimensions and ratios. Pre-merge checks and finishing touches❌ Failed checks (2 warnings)
✅ Passed checks (1 passed)
✨ Finishing touches
🧪 Generate unit tests (beta)
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. Comment |
Wanli-Jiang
changed the title
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
tensorrt_llm/_torch/models/modeling_nanov2vlm.py (1)
207-221: Consider adding a docstring for maintainability.The nested function
_find_closest_aspect_ratiolacks a docstring explaining its algorithm and parameters. Given the recent algorithm change, adding documentation would aid future maintenance.Example docstring:
def _find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size): + """Find the closest aspect ratio from target_ratios to the given aspect_ratio. + + Selects based on minimum absolute difference between aspect ratios. + In case of a tie, prefers ratios where the image area exceeds + 0.5 * image_size^2 * ratio[0] * ratio[1]. + + Args: + aspect_ratio: The aspect ratio of the input image (width/height). + target_ratios: List of (width_tiles, height_tiles) tuples. + width: Image width in pixels. + height: Image height in pixels. + image_size: Target tile size. + + Returns: + The best matching (width_tiles, height_tiles) tuple. + """ best_ratio_diff = float("inf")
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
tensorrt_llm/_torch/models/modeling_nanov2vlm.py(1 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_nanov2vlm.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_nanov2vlm.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_nanov2vlm.py
⏰ 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 (1)
tensorrt_llm/_torch/models/modeling_nanov2vlm.py (1)
209-220: ****The tie-breaking logic in lines 218–220 is correct. Verification confirms the code matches the HuggingFace implementation exactly (as seen in InternVL and nanoVLM repositories). When aspect ratios are equally close (
ratio_diff == best_ratio_diff), the algorithm selects the ratio that yields a larger tiled area (area > 0.5 * image_size * image_size * ratio[0] * ratio[1]), ensuring optimal canvas utilization. This is the intended behavior and requires no changes.
|
/bot run |
|
PR_Github #21575 [ run ] triggered by Bot |
|
PR_Github #21575 [ run ] completed with state |
yechank-nvidia
changed the title
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
Wanli-Jiang
force-pushed
the
user/williamj/fix-nanov2vlm
branch
from
20fead8 to
5e71da6
Compare
|
/bot run |
|
PR_Github #21664 [ run ] triggered by Bot |
|
PR_Github #21664 [ run ] completed with state |
|
/bot run |
|
PR_Github #21682 [ run ] triggered by Bot |
|
PR_Github #21682 [ run ] completed with state |
|
/bot run |
|
PR_Github #21701 [ run ] triggered by Bot. Commit: |
|
PR_Github #21701 [ run ] completed with state |
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
3 participants
Root cause: the HF codes are updated for
best_ratiocalculation.Summary by CodeRabbit
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)
Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
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 thestage-listparameter 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.mdand the
scripts/test_to_stage_mapping.pyhelper.kill
killKill all running builds associated with pull request.
skip
skip --comment COMMENTSkip 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-pipelineReuse 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.