Nvidia Python Packages

nemo-relay

Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls.

6.9M 192 81

nvidia-cutlass-dsl-libs-base

CUDA Templates and Python DSLs for High-Performance Linear Algebra

4.7M 11K 2K

nvidia-cutlass-dsl

CUDA Templates and Python DSLs for High-Performance Linear Algebra

4.1M 11K 2K

nvidia-cudnn-frontend

cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.

3.4M 965 304

flashinfer-python

FlashInfer: Kernel Library for LLM Serving

3.1M 7K 2K

nvidia-cutlass-dsl-libs-cu13

CUDA Templates and Python DSLs for High-Performance Linear Algebra

3M 11K 2K

nvidia-cutlass-dsl-libs-cu12

CUDA Templates and Python DSLs for High-Performance Linear Algebra

2.9M 11K 2K

nvidia-cutlass-dsl-libs-core

CUDA Templates and Python DSLs for High-Performance Linear Algebra

2.7M 11K 2K

nccl4py

Optimized primitives for collective multi-GPU communication

1.6M 5K 1K

warp-lang

A Python framework for GPU-accelerated simulation, robotics, and machine learning.

1.3M 7K 651

flashinfer-cubin

FlashInfer: Kernel Library for LLM Serving

1.2M 7K 2K

tensorrt-cu12

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

536K 13K 2K

nemoguardrails

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

536K 7K 866

tensorrt-cu12-libs

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

273K 13K 2K

tensorrt-cu12-bindings

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

269K 13K 2K

onnx-graphsurgeon

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

257K 13K 2K

tensorrt

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

251K 13K 2K

libcuml-cu12

NVIDIA cuML: GPU-Accelerated Machine Learning

232K 5K 687

nvitop

An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.

230K 7K 249

cuml-cu12

NVIDIA cuML: GPU-Accelerated Machine Learning

222K 5K 687

tensorrt-cu13

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

219K 13K 2K

tensorrt-cu13-libs

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

206K 13K 2K

polygraphy

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

187K 13K 2K

tensorrt-cu13-bindings

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

177K 13K 2K