[None][chore] AutoDeploy: replace HF's deprecated keyword torch_dtype --> dtype #8510
Conversation
|
/bot run |
lucaslie
force-pushed
the
ll/torch_dtype_deprecation
branch
from
81aeb50 to
47140c1
Compare
📝 WalkthroughWalkthroughThe PR refactors dtype specification in HuggingFace model loading. Dtype normalization moves from initialization time to config-update time, converting string dtype values to torch.dtype objects. The parameter key shifts from "torch_dtype" to "dtype" across implementation and tests. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes The changes are well-localized with straightforward refactoring: dtype normalization relocates from initialization to config updates, and parameter keys rename consistently across files. Test updates are repetitive. Minimal review complexity, though understanding the rationale for the normalization shift requires brief context. 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 |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
tensorrt_llm/_torch/auto_deploy/models/hf.py(2 hunks)tests/unittest/_torch/auto_deploy/_utils_test/_model_test_utils.py(2 hunks)tests/unittest/_torch/auto_deploy/unit/singlegpu/models/test_hybrid_patches.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:
tests/unittest/_torch/auto_deploy/unit/singlegpu/models/test_hybrid_patches.pytests/unittest/_torch/auto_deploy/_utils_test/_model_test_utils.pytensorrt_llm/_torch/auto_deploy/models/hf.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:
tests/unittest/_torch/auto_deploy/unit/singlegpu/models/test_hybrid_patches.pytests/unittest/_torch/auto_deploy/_utils_test/_model_test_utils.pytensorrt_llm/_torch/auto_deploy/models/hf.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:
tests/unittest/_torch/auto_deploy/unit/singlegpu/models/test_hybrid_patches.pytests/unittest/_torch/auto_deploy/_utils_test/_model_test_utils.pytensorrt_llm/_torch/auto_deploy/models/hf.py
🧠 Learnings (1)
📓 Common learnings
Learnt from: ixlmar
PR: NVIDIA/TensorRT-LLM#8263
File: examples/models/contrib/sdxl/run_sdxl.py:0-0
Timestamp: 2025-10-13T13:55:04.170Z
Learning: The `diffusers` library (e.g., `DiffusionPipeline`, `StableDiffusionXLPipeline`, `StableDiffusion3Pipeline`) uses the `torch_dtype` parameter in `from_pretrained()` calls, not `dtype`. Only the `transformers` library has migrated to using `dtype`.
🔇 Additional comments (3)
tensorrt_llm/_torch/auto_deploy/models/hf.py (1)
276-276: LGTM! Correct migration todtypefor transformers.The change from
torch_dtypetodtypeis correct for thetransformerslibrary, which has migrated to the new parameter name. HuggingFace'sfrom_pretrainedwill handle the"auto"value appropriately.Based on learnings
tests/unittest/_torch/auto_deploy/unit/singlegpu/models/test_hybrid_patches.py (1)
51-51: LGTM! Test updated consistently with implementation.The change from
torch_dtypetodtypealigns with the implementation changes inhf.py. The concrete dtype value"bfloat16"will be correctly converted totorch.bfloat16by the_recursive_update_configlogic.tests/unittest/_torch/auto_deploy/_utils_test/_model_test_utils.py (1)
468-468: LGTM! Model configs updated consistently.Both model configurations correctly updated from
torch_dtypetodtype. The changes align with the implementation inhf.pyand ensure test coverage for the new parameter name across different model types.Also applies to: 487-487
|
PR_Github #21943 [ run ] triggered by Bot. Commit: |
… --> dtype Signed-off-by: Lucas Liebenwein <[email protected]>
lucaslie
force-pushed
the
ll/torch_dtype_deprecation
branch
from
47140c1 to
c1e4528
Compare
|
/bot run |
|
PR_Github #21944 [ run ] triggered by Bot. Commit: |
|
PR_Github #21943 [ run ] completed with state |
|
PR_Github #21944 [ run ] completed with state |
|
/bot run |
|
PR_Github #21952 [ run ] triggered by Bot. Commit: |
|
PR_Github #21952 [ run ] completed with state |
|
/bot run |
|
PR_Github #22074 [ run ] triggered by Bot. Commit: |
|
PR_Github #22074 [ run ] completed with state |
|
/bot run |
|
PR_Github #22082 [ run ] triggered by Bot. Commit: |
|
PR_Github #22082 [ run ] completed with state |
… --> dtype (NVIDIA#8510) Signed-off-by: Lucas Liebenwein <[email protected]> Signed-off-by: yufeiwu-nv <[email protected]>
… --> dtype (NVIDIA#8510) Signed-off-by: Lucas Liebenwein <[email protected]>
… --> dtype (NVIDIA#8510) Signed-off-by: Lucas Liebenwein <[email protected]>
… --> dtype (NVIDIA#8510) Signed-off-by: Lucas Liebenwein <[email protected]>
… --> dtype (NVIDIA#8510) Signed-off-by: Lucas Liebenwein <[email protected]>
5 participants
HF is deprecating the
torch_dtypekeyword. This PR is a follow-up to #8263 where it was already deprecated for the PT backend to address the deprecation in AutoDeploy as wellSummary 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.
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 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.