← voltar

categoria

Model serving

Serve trained machine learning models behind an API, with batching, scaling and versioning.

Lado a lado

Model serving
FerramentaEstrelasLicençaTermosAuto-hospedadoLinguagemÚltima releaseÚltimo push
Triton Inference Server11kBSD-3-ClauseCódigo abertoSimPythonv2.73.02026-10-06
BentoML8.9kApache-2.0Código abertoSimPythonv1.4.392026-10-05
KServe6.1kApache-2.0Código abertoSimGov0.21.02026-10-06
MLServer900Apache-2.0Código abertoSimPython1.7.12026-10-05

4 ferramentas

BentoML

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

Linguagem
Python
Licença
Apache-2.0
Estrelas
8.9k
Última release
v1.4.39
Último push
2026-10-05
KServe

Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes

Linguagem
Go
Licença
Apache-2.0
Estrelas
6.1k
Última release
v0.21.0
Último push
2026-10-06
MLServer

An inference server for your machine learning models, including support for multiple frameworks, multi-model serving and more

Linguagem
Python
Licença
Apache-2.0
Estrelas
900
Última release
1.7.1
Último push
2026-10-05

O que essas ferramentas substituem