Skip to content

Comments

[https://nvbugs/5762336][fix] support to parse the keyword modules_to_not_convert of the HF model config"#10527

Merged
xxi-nv merged 1 commit intoNVIDIA:mainfrom
xxi-nv:parseHFConfig
Jan 13, 2026
Merged

[https://nvbugs/5762336][fix] support to parse the keyword modules_to_not_convert of the HF model config"#10527
xxi-nv merged 1 commit intoNVIDIA:mainfrom
xxi-nv:parseHFConfig

Conversation

@xxi-nv
Copy link
Collaborator

@xxi-nv xxi-nv commented Jan 8, 2026

…_not_convert in the HF model config

Summary by CodeRabbit

  • Bug Fixes
    • Improved quantization configuration handling to respect user-provided exclude modules settings instead of unconditionally overwriting them for FP8 and MXFP4 quantization. Added intelligent default module exclusions that adapt based on model backend and configuration.

✏️ Tip: You can customize this high-level summary in your review settings.

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

  • 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.

Details

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.

@xxi-nv xxi-nv requested a review from a team as a code owner January 8, 2026 03:06
@xxi-nv xxi-nv requested review from lfr-0531 and yilin-void January 8, 2026 03:06
@coderabbitai
Copy link
Contributor

coderabbitai bot commented Jan 8, 2026

📝 Walkthrough

Walkthrough

Modified quantization configuration handling in a single module to conditionally set default exclude_modules values based on quantization type and backend, instead of unconditionally overwriting them. Now respects pre-existing configuration values when reading from Hugging Face quantization metadata.

Changes

Cohort / File(s) Change Summary
Quantization configuration defaults
tensorrt_llm/_torch/model_config.py
Modified load_hf_quant_config to extract exclude_modules from modules_to_not_convert. Added conditional logic in FP8 path to set backend-specific defaults (moe_backend-dependent). Added conditional logic in MXFP4 path to set model-specific defaults. Removed unconditional exclude_modules assignments to preserve pre-existing values.

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~20 minutes

🚥 Pre-merge checks | ✅ 1 | ❌ 2
❌ Failed checks (2 warnings)
Check name Status Explanation Resolution
Docstring Coverage ⚠️ Warning Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%. Write docstrings for the functions missing them to satisfy the coverage threshold.
Description check ⚠️ Warning The pull request description lacks substantive content. The Description and Test Coverage sections are empty, and the PR Checklist shows unchecked items. Add a clear explanation of the issue, the solution, and relevant test cases. Complete the PR Checklist items as appropriate for this change.
✅ Passed checks (1 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly and specifically summarizes the main change: adding support to parse the modules_to_not_convert keyword from HF model configuration. It follows the required format with NVBugs ID and [fix] type.

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

✨ Finishing touches
  • 📝 Generate docstrings

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.

@xxi-nv
Copy link
Collaborator Author

xxi-nv commented Jan 8, 2026

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #30981 [ run ] triggered by Bot. Commit: 8d30848

@xxi-nv xxi-nv requested a review from syuoni January 8, 2026 06:30
@tensorrt-cicd
Copy link
Collaborator

PR_Github #30981 [ run ] completed with state SUCCESS. Commit: 8d30848
/LLM/main/L0_MergeRequest_PR pipeline #23937 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

@xxi-nv
Copy link
Collaborator Author

xxi-nv commented Jan 8, 2026

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31130 [ run ] triggered by Bot. Commit: 8d30848

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31130 [ run ] completed with state SUCCESS. Commit: 8d30848
/LLM/main/L0_MergeRequest_PR pipeline #24047 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

@xxi-nv
Copy link
Collaborator Author

xxi-nv commented Jan 9, 2026

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31211 [ run ] triggered by Bot. Commit: d202af8

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31211 [ run ] completed with state SUCCESS. Commit: d202af8
/LLM/main/L0_MergeRequest_PR pipeline #24122 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

@xxi-nv
Copy link
Collaborator Author

xxi-nv commented Jan 10, 2026

/bot run --disable-fail-fast

@xxi-nv xxi-nv enabled auto-merge (squash) January 10, 2026 14:35
@tensorrt-cicd
Copy link
Collaborator

PR_Github #31358 [ run ] triggered by Bot. Commit: d202af8

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31358 [ run ] completed with state SUCCESS. Commit: d202af8
/LLM/main/L0_MergeRequest_PR pipeline #24248 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

@xxi-nv
Copy link
Collaborator Author

xxi-nv commented Jan 11, 2026

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31393 [ run ] triggered by Bot. Commit: 26a79b9

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31393 [ run ] completed with state DISABLED
CI server is currently disabled for scheduled maintenance. Estimated completion time: 8 AM PST on 1/11.

@xxi-nv
Copy link
Collaborator Author

xxi-nv commented Jan 11, 2026

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31407 [ run ] triggered by Bot. Commit: 26a79b9

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31407 [ run ] completed with state SUCCESS. Commit: 26a79b9
/LLM/main/L0_MergeRequest_PR pipeline #24268 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

@xxi-nv
Copy link
Collaborator Author

xxi-nv commented Jan 12, 2026

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31435 [ run ] triggered by Bot. Commit: 26a79b9

…_not_convert in the HF model config

Signed-off-by: xxi <xxi@nvidia.com>
@xxi-nv
Copy link
Collaborator Author

xxi-nv commented Jan 12, 2026

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31462 [ run ] triggered by Bot. Commit: 0331c81

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31435 [ run ] completed with state ABORTED. Commit: 26a79b9
LLM/main/L0_MergeRequest_PR #24296 (Blue Ocean) completed with status: ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31462 [ run ] completed with state SUCCESS. Commit: 0331c81
/LLM/main/L0_MergeRequest_PR pipeline #24322 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

@xxi-nv
Copy link
Collaborator Author

xxi-nv commented Jan 12, 2026

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31630 [ run ] triggered by Bot. Commit: 0331c81

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31630 [ run ] completed with state SUCCESS. Commit: 0331c81
/LLM/main/L0_MergeRequest_PR pipeline #24461 completed with status: 'SUCCESS'

@xxi-nv xxi-nv merged commit ba1037c into NVIDIA:main Jan 13, 2026
5 checks passed
@xxi-nv xxi-nv deleted the parseHFConfig branch January 13, 2026 01:56
videodanchik pushed a commit to videodanchik/TensorRT-LLM that referenced this pull request Jan 14, 2026
…_not_convert of the HF model config" (NVIDIA#10527)

Signed-off-by: xxi <xxi@nvidia.com>
Signed-off-by: Daniil Kulko <kulkodaniil@gmail.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.

3 participants