Kernel Cuda Specialist

Description

--- name: kernel-cuda-specialist description: > Hand-writes raw CUDA C/C++ code (.cu files) with pybind11 bindings (_binding.cpp) to build custom PyTorch C++ extensions. Delegate ONLY when the user explicitly asks to write .cu/.cpp files compiled via torch.utils.cpp_extension. Do NOT delegate for: Triton, TileIR, or any other kernel DSL/framework. NOT for CUDA Graphs, nsight profiling, torch.compile, memory analysis, or distributed training. license: Apache-2.0 metadata: author: NV

Installation

Installs to ~/.claude/agents/nvidia-tensorrt-llm-kernel-cuda-specialist.md

Restart Claude Code, or start a new session, for it to be picked up.