TensorRT
Last updated
, generated by Sumble
Explore more → **TensorRT**
What is TensorRT?
TensorRT is an SDK 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 applications. It is commonly used to optimize trained neural networks from various frameworks (TensorFlow, PyTorch, etc.) for deployment in production environments, especially on NVIDIA GPUs.
What other technologies are related to TensorRT?
TensorRT Competitor Technologies
OpenVINO
OpenVINO is a toolkit for optimizing and deploying deep learning models, competing with TensorRT in terms of model optimization and inference acceleration on different hardware.
ONNX Runtime
ONNX Runtime is an inference engine that can execute ONNX models, providing an alternative to TensorRT for deploying machine learning models.
TVM
TVM is a compiler framework for machine learning systems, offering an alternative approach to optimizing and deploying models, competing with TensorRT.
IREE
No summary available
IREE (Intermediate Representation Execution Environment) is a compiler infrastructure and runtime for machine learning models, providing an alternative deployment path to TensorRT.
XLA
XLA (Accelerated Linear Algebra) is a compiler for TensorFlow graphs, which can be an alternative optimization and deployment path for TensorFlow models compared to using TensorRT.
ONNXRuntime
ONNX Runtime is an inference engine that can execute ONNX models, providing an alternative to TensorRT for deploying machine learning models. (Same as ONNX Runtime).
TFLite
TFLite is TensorFlow's solution for mobile and embedded devices, often competing with TensorRT for similar deployment scenarios.
CoreML
CoreML is Apple's machine learning framework, which can be used to deploy models on Apple devices, serving as an alternative to TensorRT in that ecosystem.
Number of organizations that mention technology
ⓘ Tap on a tech to explore matching organizations
TensorRT Complementary Technologies
ONNX
ONNX is a standard for representing machine learning models, and TensorRT can ingest and optimize ONNX models for deployment.
cuDNN
cuDNN is a library of optimized primitives for deep learning, which TensorRT uses to accelerate computations.
CUDA
CUDA is NVIDIA's parallel computing platform and programming model, and TensorRT is built on top of CUDA.
Number of organizations that mention technology
ⓘ Tap on a tech to explore matching organizations
Which job functions commonly mention TensorRT?
Machine Learning
1.6% of all Machine Learning jobs mention TensorRT
View 1.6k
jobs on Sumble
AI Engineer
0.8% of all AI Engineer jobs mention TensorRT
View 678
jobs on Sumble
MLOps Engineer
0.7% of all MLOps Engineer jobs mention TensorRT
View 56
jobs on Sumble
Engineering & R&D
1156 Engineering & R&D jobs mention TensorRT
View 1.2k
jobs on Sumble
Engineer
1069 Engineer jobs mention TensorRT
View 1.1k
jobs on Sumble
Which organizations are mentioning TensorRT?
Aurora Innovation
Scientific and Technical Services
See more or filter by date, location, industry, etc →
Summary powered by 
Sumble
Sumble Find the right accounts, contact, message, and time to sell
Whether you're looking to get your foot in the door, find the right person to talk to, or close the deal — accurate, detailed, trustworthy, and timely information about the organization you're selling to is invaluable.
Use Sumble to: