{"categories":[{"label":"Python Modules","url":"https://skillfed.io/packages/category/software-development-libraries-python-modules/4"},{"label":"Artificial Intelligence","url":"https://skillfed.io/packages/category/scientific-engineering-artificial-intelligence/2"}],"enrichment":{"capability":"Provides Python and C++ APIs to NVIDIA's cuDNN library, exposing high-performance GPU kernels for scaled dot-product attention, grouped matrix multiplication for mixture-of-experts training, and fused operations optimized for Hopper and Blackwell GPUs.","skillfed_tags":["gpu-acceleration","transformer-kernels","quantization"],"use_cases":["Accelerate transformer attention mechanisms in large language models using SDPA kernels optimized for Hopper and Blackwell GPUs.","Train mixture-of-experts models efficiently with fused grouped GEMM operations that reduce memory bandwidth and kernel launch overhead.","Deploy quantized deep learning models using FP8 and MXFP8 precision kernels for reduced memory footprint and faster inference.","Build custom GPU kernels by inspecting and modifying open-source implementations like FROST GEMM and block-sparse attention.","Integrate cuDNN-accelerated operations into PyTorch models with automatic differentiation and torch.compile support."],"what_it_does":"nvidia-cudnn-frontend is NVIDIA's modern entry point to cuDNN, offering both a header-only C++ API and Python bindings that abstract the complexity of the cuDNN Graph API. It exposes state-of-the-art GPU kernels including scaled dot-product attention (SDPA/Flash Attention), grouped GEMM fusions for mixture-of-experts training, fused normalization and activation operations, and quantized matrix multiplication in FP8 and MXFP8 precision. The package targets NVIDIA's latest GPU architectures\u2014Hopper (H100/H200) and Blackwell (B200/GB200/GB300)\u2014and includes native PyTorch integration with torch.compile support.\n\nThe package ships with open-source kernel implementations (FROST GEMM engine, block-sparse attention, native sparse attention, and fused RMSNorm+SiLU) that developers can inspect, modify, and contribute to. Installation is simple via pip, though it requires NVIDIA driver, CUDA Toolkit, and cuDNN 8.5.0 or later on the system. The library is actively maintained with prebuilt wheels for modern Python versions and multiple architectures.","worth_installing":"Yes. The package is actively maintained, dual-licensed under permissive terms, has no known vulnerabilities, and provides essential optimized kernels for modern GPU workloads. Install it if you are training or deploying deep learning models on NVIDIA Hopper or Blackwell GPUs and need high-performance attention, grouped GEMM, or quantized operations. The requirement for CUDA Toolkit and cuDNN 8.5.0+ is a prerequisite, not a drawback\u2014it reflects the package's tight integration with NVIDIA's GPU stack."},"id":"nvidia-cudnn-frontend","links":{"html":"https://skillfed.io/packages/nvidia-cudnn-frontend","md":"https://skillfed.io/packages/nvidia-cudnn-frontend.md","pypi":"https://pypi.org/project/nvidia-cudnn-frontend/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-08-06","license_spdx":null,"license_treatment":"permissive","name":"nvidia-cudnn-frontend","python_support":"supports_current","summary":"NVIDIA cuDNN Frontend \u2014 Python and C++ Graph API with SOTA attention (SDPA / Flash Attention), MoE grouped GEMM fusions, and FP8/MXFP8 kernels for Hopper and Blackwell GPUs."},"popularity":{"monthly_downloads":4479592,"position":2292,"tier":"top_5000"},"security":{"n_vulnerabilities":0},"version":"1.27.0"}