📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)

**/*.{cpp,h,hpp,cc,cxx}: Closing braces of namespaces should have a comment saying the namespace it closes (e.g., } // namespace foo)
Prefer const or constexpr variables over #defines whenever possible, as the latter are not visible to the compiler.
A variable that is not modified after its initialization should be declared as const.
Except 0 (only used in comparison for checking signness/existence/emptiness) and nullptr, true, false, all other literals should only be used for variable initialization.
Use the Allman indentation style for braces.
Put the semicolon for an empty for or while loop in a new line.
The statement forming the body of a switch, while, do .. while or for statement shall be a compound statement (use brace-delimited statements).
If and else should always be followed by brace-delimited statements, even if empty or a single statement.
C++ filenames should use camel case with first letter lowercase (e.g., thisIsAFilename.cpp), and all files involved in the compilation of a target must have filenames that are case-insensitive unique.
All types (including class names) are camel case with uppercase first letter (e.g., FooBarClass).
Local variables, methods, and namespaces use camel case with first letter lowercase (e.g., localFooBar).
Non-magic-number global variables that are non-static and not defined in anonymous namespace use camel case prefixed by a lower case 'g' (e.g., gDontUseGlobalFoos).
Non-magic-number global variables that are static or defined in an anonymous namespace use camel case prefixed by a lower case 's' (e.g., sMutableStaticGlobal).
Locally visible static variable uses camel case with lowercase prefix 's' as the first letter of the name (e.g., static std::once_flag sFlag;).
Class member variables use camel case prefixed with an 'm' (e.g., mNbFooValues). Public member variables do not require the 'm' prefix but it is encouraged for clarity.
Enumerations, global constants, static constants at class-scope, and function-scope magic...

Files:

• cpp/tensorrt_llm/nanobind/batch_manager/algorithms.cpp
• cpp/tests/runtime/gptDecoderBatchedTest.cpp
• cpp/tensorrt_llm/batch_manager/trtGptModelInflightBatching.cpp
• cpp/tensorrt_llm/pybind/batch_manager/algorithms.cpp
• cpp/include/tensorrt_llm/runtime/request.h
• cpp/include/tensorrt_llm/batch_manager/createNewDecoderRequests.h
• cpp/tensorrt_llm/batch_manager/createNewDecoderRequests.cpp

📄 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:

• cpp/tensorrt_llm/nanobind/batch_manager/algorithms.cpp
• cpp/tests/runtime/gptDecoderBatchedTest.cpp
• tensorrt_llm/_torch/pyexecutor/sampler.py
• cpp/tensorrt_llm/batch_manager/trtGptModelInflightBatching.cpp
• cpp/tensorrt_llm/pybind/batch_manager/algorithms.cpp
• cpp/include/tensorrt_llm/runtime/request.h
• cpp/include/tensorrt_llm/batch_manager/createNewDecoderRequests.h
• cpp/tensorrt_llm/batch_manager/createNewDecoderRequests.cpp

📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)

**/*.py: The code developed for TensorRT-LLM 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 class in the constructor in Python.
For interfaces that may be used outside a file, prefer docstrings over comments in Python.
Comments in Python should be reserved for code within a function, or interfaces that are local to a file.
Use Google style docstrings for classes and functions in Python, which can be parsed by Sphinx.
Attributes and variables in Python can be documented inline; attribute docstrings will be rendered under the docstring for the class.
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/_torch/pyexecutor/sampler.py

📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)

Use a preprocessor guard in header files. The guard name must have prefix TRTLLM_ followed by the filename, all in caps, and no trailing underscore.

Files:

• cpp/include/tensorrt_llm/runtime/request.h
• cpp/include/tensorrt_llm/batch_manager/createNewDecoderRequests.h

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/_torch/pyexecutor/sampler.py
• cpp/tensorrt_llm/batch_manager/trtGptModelInflightBatching.cpp
• cpp/include/tensorrt_llm/runtime/request.h
• cpp/tensorrt_llm/batch_manager/createNewDecoderRequests.cpp

📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)

**/*.{cpp,cxx,cc,cu,h,hpp,hxx,hh,cuh}: In C++, close namespaces with a comment naming the namespace (e.g., } // namespace foo)
Prefer const/constexpr variables over #define for constants
Declare variables const if not modified after initialization
Use Allman brace style in C++
C++ filenames use lowerCamelCase and must be case-insensitively unique within a build target
C++ type names use UpperCamelCase
Local variables, methods, and namespaces use lowerCamelCase
Global non-static variables not in anonymous namespace use gPrefix lowerCamelCase (e.g., gExample)
Static globals or globals in anonymous namespaces use sPrefix lowerCamelCase
Locally visible static variables start with 's' (e.g., static std::once_flag sFlag;)
Member variables use mPrefix lowerCamelCase; public members may omit but are encouraged to use 'm'
Constants (enums, global/static/function-scope magic numbers) use kPREFIXED_UPPER_SNAKE (e.g., kDIGIT_NUM)
If macros are unavoidable, use UPPER_SNAKE_CASE (prefer constants over #define)
Constructor parameter that conflicts with a public member name gets trailing underscore (foo_)
Literal suffixes should be uppercase (e.g., 1234L not 1234l)
C++: use spaces only; indent 4 spaces
Run clang-format (LLVM style) before submitting; wrap lines at 120 characters
If formatting must be bypassed, use // clang-format off/on around the section
Prefer smart pointers; use unique_ptr for sole ownership, shared_ptr for shared; weak_ptr only in exceptional cases
Do not use deprecated pre-C++11 smart pointers
Use C++ style comments; avoid C comments except special inline cases; prefer // single-line
Capitalize and punctuate full-sentence comments
Follow Doxygen rules: use //! for comments and //!< for members in C++
Disable code with #if/#endif and mnemonic conditions; avoid commented-out code; avoid dead code
Do not throw exceptions across library boundaries
Use least-forceful casts; avoid removing const/volatile; avoid C-style and functional casts (except constructors); p...

Files:

• cpp/tensorrt_llm/runtime/decoderState.cpp
• cpp/include/tensorrt_llm/batch_manager/createNewDecoderRequests.h
• cpp/tensorrt_llm/batch_manager/createNewDecoderRequests.cpp

📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)

**/*.{cpp,cxx,cc,cu}: Avoid literal values except for 0, nullptr, true, false; use named constexpr for other literals
Place semicolon of empty for/while loop on a new line
Always use brace-delimited bodies for switch/while/do-for/if/else
Use inline C comments in argument lists when parameter meaning is unclear (e.g., /* checkForErrors = */ false)
Do not use assignment in subexpressions (e.g., if (x = y) ... is forbidden)
Switch on enums should enumerate all values and omit default to catch new values at compile time
Structure switch statements; prohibit fallthrough except between empty cases; each case ends with break or throw; return at end of case not allowed; put break inside braces for compound case
Prefer anonymous namespaces over static for internal linkage of functions
Every defined function must be called at least once (no unused methods)

Files:

• cpp/tensorrt_llm/runtime/decoderState.cpp
• cpp/tensorrt_llm/batch_manager/createNewDecoderRequests.cpp

📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)

Parameter names must be consistent between declarations and definitions

Files:

• cpp/tensorrt_llm/runtime/decoderState.cpp
• cpp/include/tensorrt_llm/batch_manager/createNewDecoderRequests.h
• cpp/tensorrt_llm/batch_manager/createNewDecoderRequests.cpp

📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)

Prepend NVIDIA copyright header (current year) to all source files

Files:

• cpp/tensorrt_llm/runtime/decoderState.cpp
• cpp/include/tensorrt_llm/batch_manager/createNewDecoderRequests.h
• cpp/tensorrt_llm/batch_manager/createNewDecoderRequests.cpp

📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)

Header files must use include guards named TRTLLM__H without underscores prefix/suffix (e.g., TRTLLM_FOO_BAR_HELLO_H)

Files:

• cpp/include/tensorrt_llm/batch_manager/createNewDecoderRequests.h