OpenVINO
E813078
OpenVINO is an open-source toolkit from Intel for optimizing and deploying deep learning inference across a range of hardware platforms, especially Intel CPUs, integrated GPUs, VPUs, and FPGAs.
All labels observed (10)
| Label | Occurrences |
|---|---|
| OpenVINO canonical | 2 |
| Intel Computer Vision SDK | 1 |
| Intel OpenVINO toolkit | 1 |
| Model Optimizer (legacy component) | 1 |
| OpenVINO (via import) | 1 |
| OpenVINO IR | 1 |
| OpenVINO Model Server | 1 |
| OpenVINO Runtime | 1 |
| Vitis AI | 1 |
| https://github.com/openvinotoolkit/openvino | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T9675003 — 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: OpenVINO Context triple: [NVIDIA Triton Inference Server, supportsFramework, OpenVINO]
-
A.
NVIDIA TensorRT
NVIDIA TensorRT is a high-performance deep learning inference optimizer and runtime library designed to accelerate AI models on NVIDIA GPUs in production environments.
-
B.
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.
-
C.
ONNX
ONNX (Open Neural Network Exchange) is an open standard format for representing machine learning models that enables interoperability between different deep learning frameworks and tools.
-
D.
DeepStream SDK
DeepStream SDK is NVIDIA’s streaming analytics toolkit designed for building high-performance, real-time AI-powered video and sensor processing applications on GPUs and edge devices.
-
E.
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.
- 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: OpenVINO Target entity description: OpenVINO is an open-source toolkit from Intel for optimizing and deploying deep learning inference across a range of hardware platforms, especially Intel CPUs, integrated GPUs, VPUs, and FPGAs.
-
A.
NVIDIA TensorRT
NVIDIA TensorRT is a high-performance deep learning inference optimizer and runtime library designed to accelerate AI models on NVIDIA GPUs in production environments.
-
B.
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.
-
C.
ONNX
ONNX (Open Neural Network Exchange) is an open standard format for representing machine learning models that enables interoperability between different deep learning frameworks and tools.
-
D.
DeepStream SDK
DeepStream SDK is NVIDIA’s streaming analytics toolkit designed for building high-performance, real-time AI-powered video and sensor processing applications on GPUs and edge devices.
-
E.
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.
- F. None of above. chosen
Statements (88)
| Predicate | Object |
|---|---|
| instanceOf |
Intel software product
ⓘ
deep learning inference toolkit ⓘ open-source software ⓘ |
| category |
artificial intelligence framework
ⓘ
edge AI toolkit ⓘ machine learning library ⓘ |
| deploymentScenario |
cloud inference
ⓘ
edge computing ⓘ on-premise servers ⓘ |
| developer |
Intel
ⓘ
linked to:
Intel Corporation
|
| feature |
FP16 optimization
ⓘ
INT8 quantization ⓘ automatic device selection ⓘ benchmarking tools ⓘ heterogeneous execution ⓘ model compression ⓘ model optimization ⓘ multi-device inference ⓘ post-training quantization ⓘ pre-trained model zoo ⓘ runtime inference engine ⓘ |
| includesComponent |
Developer tools and samples
ⓘ
Model Optimizer (legacy component) ⓘ
linked to:
OpenVINO
Open Model Zoo ⓘ OpenVINO Model Server ⓘ
linked to:
OpenVINO
OpenVINO Runtime ⓘ
linked to:
OpenVINO
|
| initialReleaseBy |
Intel
ⓘ
linked to:
Intel Corporation
|
| license | Apache License 2.0 ⓘ |
| optimizedFor | Intel hardware ⓘ |
| origin |
Intel Computer Vision SDK
ⓘ
linked to:
OpenVINO
|
| primaryUse |
computer vision inference
ⓘ
deep learning inference optimization ⓘ deployment of AI models to edge devices ⓘ speech and NLP inference ⓘ |
| programmingLanguage |
C++
ⓘ
Python ⓘ |
| repository |
https://github.com/openvinotoolkit/openvino
ⓘ
linked to:
OpenVINO
|
| supportsAccelerationTechnique |
asynchronous inference
ⓘ
constant folding ⓘ graph-level optimizations ⓘ layer-wise optimization ⓘ operator fusion ⓘ |
| supportsAPI |
C API
ⓘ
C++ API ⓘ Python API ⓘ REST API via OpenVINO Model Server ⓘ |
| supportsDomain |
audio processing
ⓘ
computer vision ⓘ healthcare AI ⓘ industrial IoT ⓘ natural language processing ⓘ smart retail ⓘ |
| supportsFramework |
Caffe
ⓘ
MXNet ⓘ ONNX ⓘ PyTorch ⓘ TensorFlow ⓘ |
| supportsHardware |
Intel CPU
ⓘ
Intel FPGA ⓘ
linked to:
FPGA
Intel Habana Gaudi (via ONNX Runtime integration) ⓘ Intel Movidius Myriad ⓘ Intel Neural Compute Stick 2 ⓘ Intel VPU ⓘ Intel discrete GPU ⓘ Intel integrated GPU ⓘ
linked to:
Intel integrated graphics
|
| supportsLanguageBinding |
.NET
ⓘ
C ⓘ C++ ⓘ Go ⓘ Java ⓘ Node.js ⓘ Python ⓘ Rust ⓘ |
| supportsModelFormat |
ONNX
ⓘ
OpenVINO IR ⓘ
linked to:
OpenVINO
PaddlePaddle ⓘ TensorFlow Frozen Graph ⓘ
linked to:
TensorFlow GraphDef
TensorFlow SavedModel ⓘ
linked to:
TensorFlow SavedModel (via conversion)
|
| supportsOS |
Linux
ⓘ
Windows ⓘ macOS (limited, CPU-only) ⓘ
linked to:
macOS
|
| supportsPrecision |
BF16
ⓘ
FP16 ⓘ FP32 ⓘ INT8 ⓘ UINT8 ⓘ |
| website |
https://docs.openvino.ai
ⓘ
https://www.openvino.ai ⓘ |
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: OpenVINO Description of subject: OpenVINO is an open-source toolkit from Intel for optimizing and deploying deep learning inference across a range of hardware platforms, especially Intel CPUs, integrated GPUs, VPUs, and FPGAs.
Referenced by (11)
Full triples — surface form annotated when it differs from this entity's canonical label.
linked to: OpenVINO
linked to: OpenVINO
linked to: OpenVINO
linked to: OpenVINO
linked to: OpenVINO
linked to: OpenVINO
linked to: OpenVINO