Skip to content
Agentmart
Submit a tool

kernel-cuda-specialist

Subagent "kernel-cuda-specialist" from NVIDIA/TensorRT-LLM: Hand-writes raw CUDA C/C++ code (.cu files) with pybind11 bindings (_binding.cpp) to build custom…

Template by NVIDIA

IndexedNOASSERTION★ 14,937
Write a review

Install

Works with Claude Code. Read the repository before you give any tool access to your data.

curl -fsSL https://raw.githubusercontent.com/NVIDIA/TensorRT-LLM/main/.claude/agents/kernel-cuda-specialist.md -o kernel-cuda-specialist.md

Read it and adapt it to your project before use.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

A Claude Code subagent definition in NVIDIA/TensorRT-LLM. Its description says: 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, CuTe DSL, TileIR, or any other kernel DSL/framework. NOT for CUDA Graphs, nsight profiling, torch.compile, memory analysis, or distributed training.

Use cases: code-generation

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

What's in it

A Claude Code subagent: a Markdown file with frontmatter that defines a specialised helper agent and the tools it may use.

For
Claude Code
Length
46 lines
File
.claude/agents/kernel-cuda-specialist.md
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, CuTe DSL, TileIR, or any other kernel DSL/framework. NOT for CUDA Graphs, nsight profiling, torch.compile, memory analysis, or distributed training.

Sections

  1. Critical Restrictions
  2. Safe Modification Workflow

The repository's license isn't open source, so the text isn't shown here. Read it on GitHub.

Signals

Stars
14,937
Forks
2,862
Open issues
679
Last commit (this folder)
Oct 19, 2026 (9 days ago)
Last release
Apr 20, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
NOASSERTION
Repository
github.com/NVIDIA/TensorRT-LLM
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from NVIDIA

Cite this page

kernel-cuda-specialist. Agent Mart. https://agentmart.dev/templates/nvidia-tensorrt-llm-kernel-cuda-specialist (last updated 2026-10-24)