NVIDIA TensorRT
E256947
NVIDIA TensorRT is a high-performance deep learning inference optimizer and runtime library designed to accelerate AI models on NVIDIA GPUs in production environments.
All labels observed (7)
| Label | Occurrences |
|---|---|
| TensorRT | 10 |
| NVIDIA TensorRT canonical | 6 |
| NVIDIA TensorRT-LLM | 2 |
| TensorRT engine | 2 |
| NVIDIA TensorRT (indirectly via shared primitives) | 1 |
| TensorRT (CUDA-accelerated inference library) | 1 |
| TensorRT (via parsers) | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T2332716 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: NVIDIA TensorRT Context triple: [NVIDIA AI Enterprise, includes, NVIDIA TensorRT]
-
A.
NVIDIA Triton Inference Server
NVIDIA Triton Inference Server is an open-source, production-ready platform for serving and scaling AI model inference across GPUs and CPUs with support for multiple frameworks and deployment environments.
-
B.
NVIDIA AI Enterprise software suite
NVIDIA AI Enterprise software suite is a comprehensive, enterprise-grade collection of AI tools, frameworks, and optimized software designed to accelerate the development and deployment of AI and data analytics workloads across modern data centers and clouds.
-
C.
NVIDIA CUDA
NVIDIA CUDA is a parallel computing platform and programming model that enables developers to use NVIDIA GPUs for general-purpose high-performance computing.
-
D.
PlaidML
PlaidML is an open-source, hardware-agnostic deep learning engine designed to accelerate neural network computation on a wide range of GPUs and other devices.
-
E.
cuDNN
cuDNN is NVIDIA’s GPU-accelerated library of optimized primitives for deep neural networks, widely used to speed up training and inference in frameworks like TensorFlow and PyTorch.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: NVIDIA TensorRT Target entity description: NVIDIA TensorRT is a high-performance deep learning inference optimizer and runtime library designed to accelerate AI models on NVIDIA GPUs in production environments.
-
A.
NVIDIA Triton Inference Server
NVIDIA Triton Inference Server is an open-source, production-ready platform for serving and scaling AI model inference across GPUs and CPUs with support for multiple frameworks and deployment environments.
-
B.
NVIDIA AI Enterprise software suite
NVIDIA AI Enterprise software suite is a comprehensive, enterprise-grade collection of AI tools, frameworks, and optimized software designed to accelerate the development and deployment of AI and data analytics workloads across modern data centers and clouds.
-
C.
NVIDIA CUDA
NVIDIA CUDA is a parallel computing platform and programming model that enables developers to use NVIDIA GPUs for general-purpose high-performance computing.
-
D.
PlaidML
PlaidML is an open-source, hardware-agnostic deep learning engine designed to accelerate neural network computation on a wide range of GPUs and other devices.
-
E.
cuDNN
cuDNN is NVIDIA’s GPU-accelerated library of optimized primitives for deep neural networks, widely used to speed up training and inference in frameworks like TensorFlow and PyTorch.
- F. None of above. chosen
Statements (49)
| Predicate | Object |
|---|---|
| instanceOf |
deep learning inference optimizer
ⓘ
inference runtime library ⓘ |
| componentOf |
NVIDIA AI software stack
ⓘ
linked to:
NVIDIA AI Enterprise software suite
NVIDIA inference platform ⓘ |
| designedFor | production AI deployment ⓘ |
| developer |
NVIDIA
ⓘ
linked to:
NVIDIA Corporation
|
| distribution |
NVIDIA Developer website
ⓘ
NVIDIA GPU Cloud containers ⓘ |
| goal |
maximize inference throughput
ⓘ
minimize inference latency ⓘ |
| integratesWith |
CUDA
ⓘ
linked to:
NVIDIA CUDA
NVIDIA DeepStream ⓘ
linked to:
DeepStream SDK
NVIDIA Triton Inference Server ⓘ ONNX Runtime ⓘ PyTorch via ONNX export ⓘ TensorFlow via TensorRT integration ⓘ cuDNN ⓘ |
| license | proprietary ⓘ |
| optimizedFor |
NVIDIA GPUs
ⓘ
linked to:
Nvidia Maxwell GPU
|
| primaryUse | deep learning inference acceleration ⓘ |
| providesFeature |
CUDA integration
ⓘ
calibration for INT8 quantization ⓘ dynamic shapes support ⓘ dynamic tensor memory management ⓘ graph optimizations ⓘ kernel auto-tuning ⓘ layer fusion ⓘ multi-stream execution ⓘ plugin layer mechanism ⓘ |
| supportsDeploymentEnvironment |
cloud environments
ⓘ
edge devices ⓘ on-premises data centers ⓘ |
| supportsHardware |
NVIDIA data center GPUs
ⓘ
linked to:
NVIDIA Tesla data center GPUs
NVIDIA embedded GPUs ⓘ NVIDIA gaming GPUs ⓘ
linked to:
NVIDIA GeForce GPU line
|
| supportsLanguageBinding |
C++
ⓘ
Python ⓘ |
| supportsModelFormat |
NVIDIA framework-specific formats
ⓘ
ONNX ⓘ |
| supportsPrecision |
FP16
ⓘ
FP32 ⓘ INT8 ⓘ TF32 ⓘ |
| targetDomain |
computer vision inference
ⓘ
natural language processing inference ⓘ recommendation systems inference ⓘ speech and audio inference ⓘ |
| usedFor |
batch inference
ⓘ
real-time inference ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: NVIDIA TensorRT Description of subject: NVIDIA TensorRT is a high-performance deep learning inference optimizer and runtime library designed to accelerate AI models on NVIDIA GPUs in production environments.
Referenced by (23)
Full triples — surface form annotated when it differs from this entity's canonical label.
subject linked to:
NVIDIA AI Enterprise software suite
linked to: NVIDIA TensorRT
linked to: NVIDIA TensorRT
linked to: NVIDIA TensorRT
linked to: NVIDIA TensorRT
linked to: NVIDIA TensorRT
linked to: NVIDIA TensorRT
linked to: NVIDIA TensorRT
linked to: NVIDIA TensorRT
linked to: NVIDIA TensorRT
linked to: NVIDIA TensorRT
linked to: NVIDIA TensorRT
linked to: NVIDIA TensorRT
linked to: NVIDIA TensorRT
linked to: NVIDIA TensorRT
linked to: NVIDIA TensorRT
linked to: NVIDIA TensorRT