triton

Author, debug, and optimize GPU kernels with Triton in Python.

3|Updated Mar 29, 2026

Search Tags:#gpu #kernel #softmax #triton #autotune #matmul #layer-norm

Ready to run

npx skills add https://github.com/Shekswess/gpu-kernel-skills --skill triton

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: triton
Source: https://github.com/Shekswess/gpu-kernel-skills/tree/main/triton
Command: npx skills add https://github.com/Shekswess/gpu-kernel-skills --skill triton

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Triton enables developers to author, debug, and optimize GPU kernels for deep learning workloads in Python, simplifying kernel-level design and performance tuning.

Core Features & Use Cases

Kernel authoring and debugging with block-level Triton programming
Autotuning configurations for cross-GPU performance optimization
Reference and pattern resources for GEMM, fused-ops, and attention patterns

Quick Start

Launch a tiny Triton kernel, e.g., a vector add, on small tensors to verify the environment and compile success.

Frequently Asked Questions about triton

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I write a custom GPU kernel for matmul or softmax using Triton?▼

Triton enables GPU kernel authoring for matmul or softmax using block-level SPMD programming with tl.program_id and tl.load/tl.store operations. You can achieve FP32 accumulation in tl.dot for deep learning workloads.

What's the best way to optimize GPU kernel performance across different hardware?▼

The best way to optimize GPU kernel performance across different hardware is using Triton's autotuning configurations. This allows cross-GPU performance optimization by automatically selecting the best block sizes and configurations for operations like GEMM and fused-ops.

Can I integrate Triton kernels with PyTorch's torch.compile?▼

Yes, you can integrate Triton kernels with PyTorch's torch.compile. The skill supports porting kernels to torch.compile, allowing block-level SPMD programming and Triton API integration to coexist within your PyTorch deep learning workflow.

Does Triton support creating fused kernels for attention and layer norm operations?▼

Yes, Triton supports creating fused kernels for attention and layer norm operations. Developers can author, debug, and optimize fused GPU kernels using reference patterns for GEMM, fused-ops, and attention mechanisms in Python.

Why do I need block-level SPMD programming when writing GPU kernels?▼

You need block-level SPMD programming when writing GPU kernels because it simplifies kernel-level design and performance tuning. Triton uses tl.program_id for block-level programming, enabling developers to author deep learning kernels in Python without low-level CUDA C.