15 skills found
underneathall / PinferenciaPython + Inference - Model Deployment library in Python. Simplest model inference server ever.
amplab / Velox ModelserverNo description available
zhaochenyang20 / ModelServerEfficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang
eclipse-emfcloud / Emfcloud ModelserverModelserver component
typesafehub / Fdp ModelserverAn umbrella project for multiple implementations of model serving
FlinkML / Flink ModelServerGeneric Model Serving Implementation leveraging Flink
typesafehub / Fdp Beam ModelServerModel serving using Beam
eclipsesource / ModelserverServer for synchronizing (EMF-based) models in a single-user scenario
eclipse-emfcloud / Emfcloud Modelserver TheiaModelserver Theia integration
FlinkML / Flink Speculative ModelServerSpeculative model serving with Flink
LuxePlay / ModelServerAndDevelopmentPlatformThis is a comprehensive large model service platform designed to facilitate rapid deployment and application of large model services in small and medium-sized enterprises. The platform mainly includes large model service and application modules, data management modules, and development documentation modules.
zabir-nabil / Darknet Fastapi ModelserverA simple fastapi model server for darknet (yolov1 to yolov4).
bagh2178 / ModelServerA framework for deploying models remotely.
thisisclement / Prometheus TF ServingTo improve tenementary for the Tensorflow Serving (TF Serving) ModelServer instance, Prometheus serves as a telemetry app that takes in the metrics from TF Serving and displays on Graphana. This repo elaborates the needed configuration for Prometheus, Tensorflow Serving and Graphana.
13shivam / FacetronFaceTron is a high-performance face embedding server using ONNX Runtime, supporting dynamic multi-model loading, offline deployment, and scalable environments. It exposes an OpenAPI endpoint with MCP-compatible metadata and integrates with OpenTelemetry for observability.
