anthony-maio

Triton Gpu Kernel Optimization

Name: Triton Gpu Kernel Optimization
Author: anthony-maio

Development community

SOURCE https://github.com/anthony-maio/triton-skills/blob/main/skills/triton-gpu-kernel-optimization.md

Description

--- name: triton-gpu-kernel-optimization description: Write high-performance tiled Triton GPU kernels with autotune, grouped tile ordering, stride-based addressing, and proper benchmarking. --- # Tiled GEMM & General Kernel Optimization in Triton > **Targets:** Triton >= 2.1, SM70+/CDNA2+ ## Overview High-performance Triton kernels follow a consistent structure: block-tiled work distribution, stride-based pointer arithmetic, FP32 accumulation, boundary masking, and autotune sweeps. This file

Installation

Installs to ~/.claude/skills/anthony-maio-triton-skills-triton-gpu-kernel-optimization/SKILL.md

Terminal

mkdir -p ~/.claude/skills/anthony-maio-triton-skills-triton-gpu-kernel-optimization && curl -fsSL https://raw.githubusercontent.com/anthony-maio/triton-skills/HEAD/skills/triton-gpu-kernel-optimization.md -o ~/.claude/skills/anthony-maio-triton-skills-triton-gpu-kernel-optimization/SKILL.md

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