Reporium
GraphWikiTaxonomyStacksInsightsTrendsArchitectureAI-NativeFAQ
Ask anything about the repo library…
Loading repo…
←Library/LiteRT
Library/LiteRTForked

google-ai-edge/LiteRT

LiteRT

LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization

View on GitHub↗Upstream google-ai-edge/LiteRT↗

Builder

google-ai-edge

google-ai-edge

google-ai-edge • individual

Stars

2,480

Using upstream star count

Forks

325

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Sep 4, 2024

Project creation date

README Summary

<p align="center"> <img src="./g3doc/sources/litert_logo.png" alt="LiteRT Logo"/> </p>

Community Evaluation

Loading…

AI Dev Skills

Unmapped

Cross-platform ML RuntimeEdge AI DeploymentEmbedded Systems MLGenerative AI OptimizationHardware Acceleration IntegrationMobile ML InferenceModel Conversion and SerializationModel Optimization and QuantizationNeural Network CompressionOn-device Machine Learning

Tags

Cross-platform ML RuntimeEdge AI DeploymentEmbedded Systems MLGenerative AI OptimizationHardware Acceleration IntegrationMobile ML InferenceModel Conversion and SerializationModel Optimization and QuantizationNeural Network CompressionOn-device Machine LearningComputer VisionCurated ListDeep LearningDockerForkedGPU / CUDAImage GenerationLarge Language ModelsMachine LearningMobilePyTorchQuantizationReal-Time / StreamingRoadmapSecuritySegmentationTensorFlowTutorial

Taxonomy

AI Trends

On-device AIEdge ComputingModel CompressionMobile AIGenerative AI OptimizationEfficient AI Inference

category

Learning ResourcesFoundation ModelsModel TrainingInference & ServingGenerative MediaComputer VisionMLOps & InfrastructureDev Tools & AutomationSecurity & Safety

Deployment Context

Edge/MobileEmbedded SystemsOn-deviceIoT Devices

Industries

Mobile ApplicationsIoT and Embedded SystemsAutomotiveHealthcare DevicesConsumer ElectronicsRoboticsSmart HomeWearable Technology

Modalities

ImageAudioTextVideoTabularMultimodal

Skill Areas

On-device Machine LearningModel Optimization and QuantizationEdge AI DeploymentMobile ML InferenceGenerative AI OptimizationNeural Network CompressionCross-platform ML RuntimeModel Conversion and SerializationHardware Acceleration IntegrationEmbedded Systems ML

tag

Computer VisionCurated ListDeep LearningDockerForkedGPU / CUDAImage GenerationLarge Language ModelsMachine LearningMobilePyTorchQuantizationReal-Time / StreamingRoadmapSecuritySegmentationTensorFlowTutorial

Use Cases

Real-time Image Classification on MobileOn-device Speech RecognitionMobile Computer Vision ApplicationsEdge-based Natural Language ProcessingOffline AI Model InferenceEmbedded System AI IntegrationMobile Generative AI ApplicationsIoT Device Intelligence

Recent Activity

Updated 2 months ago

7 Days

0

30 Days

0

90 Days

20

Internal changes only.

Fengwu Yao • Mar 13, 2026

3af8bf6

Deprecate the TensorBuffer factory method that does not accept an Environment parameter.

Terry Heo • Mar 13, 2026

7029e96

Use TOML for GoogleTensorOptions

Terry Heo • Mar 12, 2026

cffc072

Quality

production
Quality
high
Maturity
production

Categories

Learning ResourcesPrimaryInference & ServingMLOps & InfrastructureDev Tools & AutomationSecurity & SafetyFoundation ModelsModel TrainingGenerative MediaComputer VisionEdge & Mobile AIOther AI / ML

PM Skills

Cost & EfficiencyScale & Reliability

Languages

C++100.0%

Timeline

Project created
Sep 4, 2024
Forked
Mar 13, 2026
Your last push
2 months ago
Upstream last push
16 days ago
Tracked since
Mar 13, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…