[None][fix] Migrate to new cuda binding package name #6700
Conversation
Signed-off-by: Yuan Tong <[email protected]>
📝 WalkthroughWalkthroughThe changes update CUDA-related import statements across several modules to first attempt importing from Changes
Sequence Diagram(s)sequenceDiagram
participant Module
participant cuda.bindings
participant cuda
Module->>cuda.bindings: import driver/runtime/nvrtc
alt Import succeeds
Module->>Module: Use cuda.bindings.driver/runtime/nvrtc
else Import fails
Module->>cuda: import cuda/cudart/nvrtc
Module->>Module: Use cuda/cudart/nvrtc
end
Estimated code review effort🎯 2 (Simple) | ⏱️ ~7 minutes Suggested reviewers
Note ⚡️ Unit Test Generation is now available in beta!Learn more here, or try it out under "Finishing Touches" below. 📜 Recent review detailsConfiguration used: .coderabbit.yaml 📒 Files selected for processing (9)
✅ Files skipped from review due to trivial changes (2)
🧰 Additional context used📓 Path-based instructions (2)**/*.py📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
Files:
**/*.{cpp,h,hpp,cc,cxx,cu,py}📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
Files:
🧠 Learnings (3)📚 Learning: in tensorrt-llm, test files (files under tests/ directories) do not require nvidia copyright headers...Applied to files:
📚 Learning: in tensorrt-llm testing, it's common to have both cli flow tests (test_cli_flow.py) and pytorch api ...Applied to files:
📚 Learning: in tensorrt-llm, examples directory can have different dependency versions than the root requirement...Applied to files:
⏰ 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)
🔇 Additional comments (7)
✨ Finishing Touches
🧪 Generate unit tests
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. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
Documentation and Community
|
|
/bot run |
![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
🔭 Outside diff range comments (1)
tensorrt_llm/runtime/multimodal_model_runner.py (1)
1-5: Add mandatory NVIDIA copyright headerProduction source files must include the current-year NVIDIA copyright banner.
Please prepend the required header before any imports to stay compliant.+# Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved. +# +# NVIDIA CORPORATION and its licensors retain all intellectual property +# and proprietary rights in and to this software, related documentation +# and any modifications thereto. Any use, reproduction, disclosure or +# distribution of this software and related documentation without an +# express license agreement from NVIDIA CORPORATION is strictly prohibited. + import json import os import sys
🧹 Nitpick comments (4)
tensorrt_llm/runtime/multimodal_model_runner.py (1)
17-20: Narrow the exception scope when falling back to legacycuda.cudartCatching a broad
ImportErrormay mask unrelated import problems inside the
cuda.bindings.runtimepackage. Restrict the handler to
ModuleNotFoundErrorso only the absence of the new module triggers the
fallback.-try: - from cuda.bindings import runtime as cudart -except ImportError: - from cuda import cudart +try: + from cuda.bindings import runtime as cudart +except ModuleNotFoundError: # fall back when bindings are unavailable + from cuda import cudarttensorrt_llm/_mnnvl_utils.py (1)
25-28: Narrow the exception toModuleNotFoundErrorand keep the original traceback for other import-time errorsCatching the broader
ImportErrormasks failures that occur insidecuda.bindings.driver(e.g., missing symbols), silently falling back to the legacy path and making debugging painful.
Switch toModuleNotFoundErrorso only the absence of the module triggers the fallback, and optionally log the fallback for traceability.-try: - from cuda.bindings import driver as cuda -except ImportError: - from cuda import cuda +try: + from cuda.bindings import driver as cuda # New package (cuda-python ≥13) +except ModuleNotFoundError: + # Fallback for older cuda-python versions (<13) + from cuda import cudatensorrt_llm/_torch/pyexecutor/py_executor.py (1)
15-18: UseModuleNotFoundErrorfor a precise fallback and add a short commentSame argument as above – keep unexpected import failures visible. An inline comment also explains the dual-path logic to future maintainers.
-try: - from cuda.bindings import runtime as cudart -except ImportError: - from cuda import cudart +try: + from cuda.bindings import runtime as cudart # Preferred import (cuda-python ≥13) +except ModuleNotFoundError: + from cuda import cudart # Legacy path (cuda-python <13)tensorrt_llm/auto_parallel/cluster_info.py (1)
9-12: Tighten the fallback exception scopeMirror the pattern used elsewhere so only a missing module triggers the fallback.
-try: - from cuda.bindings import runtime as cudart -except ImportError: - from cuda import cudart +try: + from cuda.bindings import runtime as cudart +except ModuleNotFoundError: + from cuda import cudart
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (7)
tensorrt_llm/_ipc_utils.py(1 hunks)tensorrt_llm/_mnnvl_utils.py(1 hunks)tensorrt_llm/_torch/pyexecutor/py_executor.py(1 hunks)tensorrt_llm/auto_parallel/cluster_info.py(1 hunks)tensorrt_llm/runtime/generation.py(1 hunks)tensorrt_llm/runtime/multimodal_model_runner.py(1 hunks)tests/microbenchmarks/all_reduce.py(1 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
**/*.py: Python code should conform to Python 3.8+.
Indent Python code with 4 spaces. Do not use tabs.
Always maintain the namespace when importing in Python, even if only one class or function from a module is used.
Python filenames should use snake_case (e.g., some_file.py).
Python classes should use PascalCase (e.g., class SomeClass).
Python functions and methods should use snake_case (e.g., def my_awesome_function():).
Python local variables should use snake_case. Prefix k for variable names that start with a number (e.g., k_99th_percentile).
Python global variables should use upper snake_case and prefix G (e.g., G_MY_GLOBAL).
Python constants should use upper snake_case (e.g., MY_CONSTANT).
Avoid shadowing variables declared in an outer scope in Python.
Initialize all externally visible members of a Python class in the constructor.
For interfaces that may be used outside a Python file, prefer docstrings over comments.
Comments in Python should be reserved for code within a function, or interfaces that are local to a file.
Use Google style docstrings for Python classes and functions, which can be parsed by Sphinx.
Attributes and variables in Python can be documented inline; attribute docstrings will be rendered under the class docstring.
Avoid using reflection in Python when functionality can be easily achieved without it.
When using try-except blocks in Python, limit the except to the smallest set of errors possible.
When using try-except blocks to handle multiple possible variable types in Python, keep the body of the try as small as possible, using the else block to implement the logic.
Files:
tensorrt_llm/_mnnvl_utils.pytensorrt_llm/runtime/multimodal_model_runner.pytests/microbenchmarks/all_reduce.pytensorrt_llm/auto_parallel/cluster_info.pytensorrt_llm/_ipc_utils.pytensorrt_llm/_torch/pyexecutor/py_executor.pytensorrt_llm/runtime/generation.py
**/*.{cpp,h,hpp,cc,cxx,cu,py}
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
All TensorRT-LLM Open Source Software code should contain an NVIDIA copyright header that includes the current year. This includes .cpp, .h, .cu, .py, and any other source files which are compiled or interpreted.
Files:
tensorrt_llm/_mnnvl_utils.pytensorrt_llm/runtime/multimodal_model_runner.pytests/microbenchmarks/all_reduce.pytensorrt_llm/auto_parallel/cluster_info.pytensorrt_llm/_ipc_utils.pytensorrt_llm/_torch/pyexecutor/py_executor.pytensorrt_llm/runtime/generation.py
🧠 Learnings (5)
📚 Learning: in tensorrt-llm, test files (files under tests/ directories) do not require nvidia copyright headers...
Learnt from: galagam
PR: NVIDIA/TensorRT-LLM#6487
File: tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py:1-12
Timestamp: 2025-08-06T13:58:07.506Z
Learning: In TensorRT-LLM, test files (files under tests/ directories) do not require NVIDIA copyright headers, unlike production source code files. Test files typically start directly with imports, docstrings, or code.
Applied to files:
tensorrt_llm/_mnnvl_utils.pytensorrt_llm/runtime/multimodal_model_runner.pytests/microbenchmarks/all_reduce.pytensorrt_llm/auto_parallel/cluster_info.pytensorrt_llm/_ipc_utils.pytensorrt_llm/_torch/pyexecutor/py_executor.pytensorrt_llm/runtime/generation.py
📚 Learning: in tensorrt-llm, examples directory can have different dependency versions than the root requirement...
Learnt from: yibinl-nvidia
PR: NVIDIA/TensorRT-LLM#6506
File: examples/models/core/mixtral/requirements.txt:3-3
Timestamp: 2025-08-01T15:14:45.673Z
Learning: In TensorRT-LLM, examples directory can have different dependency versions than the root requirements.txt file. Version conflicts between root and examples dependencies are acceptable because examples are designed to be standalone and self-contained.
Applied to files:
tensorrt_llm/_mnnvl_utils.pytensorrt_llm/runtime/multimodal_model_runner.pytests/microbenchmarks/all_reduce.pytensorrt_llm/auto_parallel/cluster_info.pytensorrt_llm/_ipc_utils.pytensorrt_llm/_torch/pyexecutor/py_executor.pytensorrt_llm/runtime/generation.py
📚 Learning: in tensorrt-llm's multimodal processing pipeline, shared tensor recovery using `from_shared_tensor()...
Learnt from: yechank-nvidia
PR: NVIDIA/TensorRT-LLM#6254
File: tensorrt_llm/_torch/pyexecutor/model_engine.py:1201-1204
Timestamp: 2025-07-22T09:22:14.726Z
Learning: In TensorRT-LLM's multimodal processing pipeline, shared tensor recovery using `from_shared_tensor()` is only needed during the context phase. Generation requests reuse the already-recovered tensor data and only need to call `strip_for_generation()` to remove unnecessary multimodal data while preserving the recovered tensors. This avoids redundant tensor recovery operations during generation.
Applied to files:
tensorrt_llm/runtime/multimodal_model_runner.py
📚 Learning: in tensorrt-llm testing, it's common to have both cli flow tests (test_cli_flow.py) and pytorch api ...
Learnt from: moraxu
PR: NVIDIA/TensorRT-LLM#6303
File: tests/integration/test_lists/qa/examples_test_list.txt:494-494
Timestamp: 2025-07-28T17:06:08.621Z
Learning: In TensorRT-LLM testing, it's common to have both CLI flow tests (test_cli_flow.py) and PyTorch API tests (test_llm_api_pytorch.py) for the same model. These serve different purposes: CLI flow tests validate the traditional command-line workflow, while PyTorch API tests validate the newer LLM API backend. Both are legitimate and should coexist.
Applied to files:
tests/microbenchmarks/all_reduce.pytensorrt_llm/runtime/generation.py
📚 Learning: applies to **/*.{cpp,h,hpp,cc,cxx,cu,py} : all tensorrt-llm open source software code should contain...
Learnt from: CR
PR: NVIDIA/TensorRT-LLM#0
File: CODING_GUIDELINES.md:0-0
Timestamp: 2025-08-06T21:22:55.018Z
Learning: Applies to **/*.{cpp,h,hpp,cc,cxx,cu,py} : All TensorRT-LLM Open Source Software code should contain an NVIDIA copyright header that includes the current year. This includes .cpp, .h, .cu, .py, and any other source files which are compiled or interpreted.
Applied to files:
tensorrt_llm/_ipc_utils.py
🔇 Additional comments (3)
tensorrt_llm/runtime/generation.py (1)
32-35: LGTM! Well-implemented migration pattern.This change correctly implements the fallback pattern to address the CUDA binding package deprecations. The try-except block attempts the new recommended import path first and gracefully falls back to the legacy import, ensuring backward compatibility while supporting the new package structure.
tests/microbenchmarks/all_reduce.py (1)
21-24: LGTM! Proper fallback import mechanism for CUDA runtime bindings.The try-except block correctly implements the migration from deprecated
cuda.cudartto the newcuda.bindings.runtimemodule, while maintaining backward compatibility. This addresses the deprecation warnings mentioned in the PR objectives.tensorrt_llm/_ipc_utils.py (1)
20-24: LGTM! Proper fallback import mechanism for CUDA bindings.The try-except block correctly implements the migration from deprecated
cuda.cudaandcuda.cudartmodules to the newcuda.bindings.driverandcuda.bindings.runtimemodules, while maintaining backward compatibility with the same interface names.
|
PR_Github #14445 [ run ] triggered by Bot |
|
PR_Github #14445 [ run ] completed with state |
Signed-off-by: Yuan Tong <[email protected]>
|
/bot run |
|
PR_Github #14479 [ run ] triggered by Bot |
|
PR_Github #14479 [ run ] completed with state |
Signed-off-by: Yuan Tong <[email protected]>
Signed-off-by: Yuan Tong <[email protected]>
Signed-off-by: Yuan Tong <[email protected]>
Signed-off-by: Yanchao Lu <[email protected]>
…6808) Signed-off-by: Yiqing Yan <[email protected]> Signed-off-by: Yanchao Lu <[email protected]> Co-authored-by: Yiqing Yan <[email protected]>
…from main (NVIDIA#6808) Signed-off-by: Yiqing Yan <[email protected]> Signed-off-by: Yanchao Lu <[email protected]> Co-authored-by: Yiqing Yan <[email protected]>
Summary by CodeRabbit
No changes to user-facing features or functionality. These updates improve internal stability and maintainability.
Description
Fix crash caused by the landed deprecations in
cuda-python==13.0.Test Coverage
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.