NVIDIA TensorRT
NVIDIA TensorRT™ is a platform for high-performance deep learning inference. It includes a deep learning inference optimizer and runtime that delivers low latency and high-throughput for deep learning inference applications. TensorRT-based applications perform up to 40x faster than CPU-only platforms during inference. With TensorRT, you can optimize neural network models trained in all major frameworks, calibrate for lower precision with high accuracy, and finally deploy to hyperscale data centers, embedded, or automotive product platforms.
TensorRT provides INT8 and FP16 optimizations for production deployments of deep learning inference applications such as video streaming, speech recognition, recommendation and natural language processing. Reduced precision inference significantly reduces application latency, which is a requirement for many real-time services, auto and embedded applications.
(Click to Zoom)
You can import trained models from every deep learning framework into TensorRT. After applying optimizations, TensorRT selects platform specific kernels to maximize performance on Tesla GPUs in the data center, Jetson embedded platforms, and NVIDIA DRIVE autonomous driving platforms.
To use AI models in data center production, the TensorRT Inference Server is a containerized microservice that maximizes GPU utilization and runs multiple models from different frameworks concurrently on a node. It leverages Docker and Kubernetes to integrate seamlessly into DevOps architectures.
With TensorRT developers can focus on creating novel AI-powered applications rather than performance tuning for inference deployment.
TensorRT Optimizations and Performance
Weight & Activation Precision Calibration
Maximizes throughput by quantizing models to INT8 while preserving accuracy
Layer & Tensor Fusion
Optimizes use of GPU memory and bandwidth by fusing nodes in a kernel
Kernel Auto-Tuning
Selects best data layers and algorithms based on target GPU platform
Dynamic Tensor Memory
Minimizes memory footprint and re-uses memory for tensors efficiently
Multi-Stream Execution
Scalable design to process multiple input streams in parallel
TensorRT dramatically accelerates deep learning inference performance on NVIDIA GPUs. See how it can power your inference needs across multiple networks with high throughput and ultra-low latency.
Widely Adopted
Integrated with All Major Frameworks
NVIDIA works closely with deep learning framework developers to achieve optimized performance for inference on AI platforms using TensorRT. If your training models are in the ONNX format or other popular frameworks such as TensorFlow and MATLAB, there are easy ways for you to import models into TensorRT for inference. Below are few integrations with information on how to get started.
TensorRT and TensorFlow are tightly integrated so you get the flexibility of TensorFlow with the powerful optimizations of TensorRT. Learn more in the TensorRT integrated with TensorFlow blog post.
MATLAB is integrated with TensorRT through GPU Coder so that engineers and scientists using MATLAB can automatically generate high-performant inference engines for Jetson, DRIVE and Tesla platforms. Learn more in this webinar.
TensorRT provides an ONNX parser so you can easily import ONNX models from frameworks such as Caffe 2, Chainer, Microsoft Cognitive Toolkit, MxNet and PyTorch into TensorRT. Learn more about ONNX support in TensorRT here.
If you are performing deep learning training in a proprietary or custom framework, use the TensorRT C++ API to import and accelerate your models. Read more in the TensorRT documentation.
NVIDIA TensorRT Inference Server
NVIDIA TensorRT Inference Server makes state-of-the-art AI-driven experiences possible in real-time. It’s an inference microservice for data center production that maximizes GPU utilization and seamlessly integrates into DevOps deployments with Docker and Kubernetes integration.
TensorRT Inference Server:
- Maximizes utilization by enabling inference for multiple models on one or more GPUs
- Supports all popular AI frameworks
- Dynamically batches requests to increase throughput
- Provides metrics for orchestration and load balancing
TensorRT Inference Server is available in a ready-to-deploy container from the NGC container registry, making it simple to use in production environments. It is also available as open source, allowing developers to customize and extend functionality of the software to fit their specific data center workflows.
With TensorRT Inference Server, there’s now a common solution for AI inference, allowing researchers to focus on creating high-quality trained models, DevOps engineers to focus on deployment, and developers to focus on their applications, without needing to reinvent the plumbing for each AI-powered application.
Learn more in the NVIDIA TensorRT Inference Server developer blog.
Download TensorRT Inference Server from the NGC container registry or access the open source project from GitHub.
(Click to Zoom)
“In our evaluation of TensorRT running our deep learning-based recommendation application on NVIDIA Tesla V100 GPUs, we experienced a 45x increase in inference speed and throughput compared with a CPU-based platform. We believe TensorRT could dramatically improve productivity for our enterprise customers.”
— Markus Noga, Head of Machine Learning at SAP
What's New in TensorRT 5 and TensorRT Inference Server
TensorRT 5 delivers up to 40x faster inference over CPU-only platforms through support for Turing GPUs, new INT8 APIs and optimizations. It uses multi-precision compute to dramatically speed up recommenders, neural machine translation, speech and natural language processing. With TensorRT 5, you can:
- Speed up inference by 40x over CPUs for models such as translation using mixed precision on Turing Tensor Cores
- Optimize inference models with new INT8 APIs and optimizations
- Deploy applications to Xavier-based NVIDIA Drive platforms and the NVIDIA DLA accelerator (FP16 only)
In addition, TensorRT 5 supports Windows and the CentOS Operating System. TensorRT 5 is available for download now to members of the NVIDIA Developer Program.
NVIDIA TensorRT inference Server is a microservice that enables applications to use AI models in data center production. Available as a ready-to-deploy container from the NGC container registry and as an open source project from GitHub, it maximizes GPU utilization, supports all popular AI models and frameworks, and integrates seamlessly into DevOps architectures.
Additional Resources
- TensorRT 4 Overview (Blog)
- sampleMNIST (Sample Code)
- sampleOnnxMNIST (Sample Code)
- SampleINT8 (Sample Code)
- Intro to RNNs in TensorRT (Video)
- Introduction to TensorRT (Webinar)
- 8-Bit Inference with TensorRT (Webinar)
- NMT with TensorRT 4 (Blog)
- Introduction PART [1, 2, 3] (Blog)
- PyTorch - RNN (Blog)
- sampleNMT (Sample Code)
- sampleCharRNN (Sample Code)
- Optimizing` NMT with TensorRT (Webinar)
- sampleMovieLens (Sample Code)
- Deep Recommender (Sample Code)
- Intro to Recommenders in TensorRT (Video)
- Deploying Deep Learning with TensorRT (Blog)
- sampleGoogleNet (Sample Code)
- sampleFasterRCNN (Sample Code)
- Deploying Networks as Services with TensorRT (Webinar)
You can find additional resources on https://devblogs.nvidia.com/tag/tensorrt/ and interact with the TensorRT developer community on the TensorRT Forum
Availability
TensorRT is freely available to members of the NVIDIA Developer Program from the TensorRT product page for development and deployment.
Developers can also get TensorRT in the TensorRT Container from the NGC container registry.
TensorRT Inference Server is available as a ready-to-deploy container from the NGC container registry and as an open source project from GitHub.
TensorRT is included in:
- NVIDIA Jetpack for Jetson TX1, TX2 embedded platforms
- NVIDIA DriveInstall for NVIDIA DRIVE PX2 autonomous driving platform
- Deepstream SDK for intelligent video analytics applications