Skip to main content
Ctrl+K
NVIDIA cuDNN Frontend - Home

NVIDIA cuDNN Frontend

NVIDIA cuDNN Frontend - Home

NVIDIA cuDNN Frontend

Table of Contents

  • Overview
  • Installation Guide
  • Samples
  • Releases Notes

Frontend API

  • Operations
    • Attention
    • Block Scaling
    • Concatenate
    • Convolutions
    • Matmul
    • Normalizations
    • Pointwise and Reduction
    • Resampling
    • Slice
  • Utilities
    • CUDA Graphs
    • Custom Execution Plan
    • Deviceless Ahead-of-time Compilation
    • Dynamic Shapes and Kernel Cache
  • Frontend OSS APIs
    • FE-OSS APIs Overview
    • GEMM Fusions
      • GEMM + Amax (SM100)
      • GEMM + SwiGLU (SM100)

Frontend Developer Guide

  • Overview
  • Core Concepts
  • Graphs
  • Hardware Forward Compatibility
  • Odds and Ends
  • Debugging

Reference

  • Supported Products
  • FAQs
  • Support
  • Software License Agreement
  • Acknowledgements
  • Notices
  • Frontend OSS APIs
  • GEMM Fusions

GEMM Fusions#

  • GEMM + Amax (SM100)
  • GEMM + SwiGLU (SM100)

previous

FE-OSS APIs Overview

next

GEMM + Amax (SM100)
NVIDIA NVIDIA
Privacy Policy | Manage My Privacy | Do Not Sell or Share My Data | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact

Copyright © 2024-2025, NVIDIA Corporation.

Last updated on Nov 13, 2025.