Library/serving
Library/servingForked

tensorflow/serving

serving

A flexible, high-performance serving system for machine learning models

Builder

tensorflow

tensorflow

tensorflow • individual

Stars

6,353

Using upstream star count

Forks

2,200

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Jan 26, 2016

Project creation date

README Summary

TensorFlow Serving is a flexible, high-performance serving system designed for production environments to serve machine learning models. It provides out-of-the-box integration with TensorFlow models and can be extended to serve other types of models and data. The system handles model lifecycle management, versioning, and provides both HTTP/REST and gRPC APIs for inference requests.

AI Dev Skills

Unmapped

Model Serving InfrastructureProduction ML SystemsDistributed Systems ArchitectureModel DeploymentRESTful API DesigngRPC Protocol ImplementationTensorFlow Model OptimizationMicroservices ArchitectureContainer OrchestrationLoad BalancingModel Versioning

Tags

Model Serving InfrastructureProduction ML SystemsDistributed Systems ArchitectureModel DeploymentRESTful API DesigngRPC Protocol ImplementationTensorFlow Model OptimizationMicroservices ArchitectureContainer OrchestrationLoad BalancingModel VersioningTabularModel Version ManagementReal-time Model InferenceREST API DevelopmentMulti-model ServingTextVideoImageModel Serving ArchitectureProduction ML InfrastructureProduction Model DeploymentML System Performance OptimizationCloud APIModel Version ControlMLOpsOn-premiseModel Deployment PipelinesSelf-hostedProduction AI SystemsBatch and Real-time InferenceAudioA/B Testing of ML ModelsServerlessBatch Prediction ServicesTensorFlow Model ManagementgRPC ServicesC++

Taxonomy

Recent Activity

Updated 3 months ago

7 Days

0

30 Days

0

90 Days

0

Quality

production
Quality
medium
Maturity
production

Categories

MLOps & InfrastructurePrimaryDev Tools & AutomationInference & ServingML Platform & InfrastructureCoding & Dev ToolsOther AI / MLModel TrainingGenerative MediaRobotics

PM Skills

Scale & ReliabilityDeveloper Platform

Languages

C++100.0%

Timeline

Project created
Jan 26, 2016
Forked
Mar 22, 2026
Your last push
3 months ago
Upstream last push
7 days ago
Tracked since
Dec 18, 2025

Similar Repos

pgvector cosine similarity · $0

Loading…