Custom CUDA kernels, Triton GPU programming, nsight profiling, memory optimization, and kernel fusion patterns.
This skill should be used when the user asks to "update documentation for my changes", "check docs for this PR", "what d...
Write docstrings for PyTorch functions and methods following PyTorch conventions. Use when writing or updating docstring...
Convert PyTorch AT_DISPATCH macros to AT_DISPATCH_V2 format in ATen C++ code. Use when porting AT_DISPATCH_ALL_TYPES_AND...