NVIDIA/TensorRT-Model-Connect

From PyTorch model to end-to-end TensorRT inference experience in two commands—AI-native, cross-platform, and built for the best possible user experience.

236

stars

1,317

commits

Python

primary language

Sep 8, 2026

updated

nvidia.github.io/TensorRT-Model-Connect/

ai-agents

ai-native

cpp

huggingface

inference

pytorch

Contributors

946 commits

211 commits

42 commits

37 commits

Similar repos

ai-dynamo/aitune

NVIDIA AITune is an inference toolkit designed for tuning and deploying Deep Learning models with a…

281

facebookincubator/AITemplate

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++…

4,724

Tencent-Hunyuan/TensorRT-libs

Model

ucb-bar/model2MLIR

Any model in Torch or JAX format to MLIR frontend dialects.

NVIDIA/TensorRT-LLM

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs)…

14,591

same org

NVIDIA/TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit…

3,532

same org

NVIDIA/TensorRT-Model-Optimizer

A unified library of SOTA model optimization techniques like quantization, distillation, pruning,…

3,785

same org

NVIDIA/FasterTransformer

Transformer related optimization, including BERT, GPT

6,446

same org

Languages

Python

54.6%

C++

43.2%

Cuda

1.4%