Kubernetes custom resource definition for serving ML models on arbitrary frameworks.
Directory
Search results
Published directory entries matching your search.
Open source MLOps project that eases model handoffs between data scientist and DevOps.
Standardized Serverless ML Inference Platform on Kubernetes.
Open-source all-in-one platform for engineering AI products. Traces, Evals, Datasets, Labels.
Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!
Neural network inference from the command line, implemented in CHICKEN Scheme.
A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.
Version and deploy your ML models following GitOps principles.
Open source MLOps platform that helps you collaborate, reproduce and share your ML work.
Machine learning model serving framework with dynamic batching and pipelined stages, provides an easy-to-use Python interface.
Proof-of-concept OpenAI Gym environment for Neural Architecture Search (NAS).
Ncnn is a high-performance neural network inference framework optimized for the mobile platform.
Easy-to-use library to boost AI inference.
A framework providing the right abstractions to ease research, development, and deployment of your ML pipelines.
An Easy-to-Use and High-Performance AI deployment framework.
Neural networks framework in pure C: training and inference, no dependencies.
Open-source GenAI and LLM observability platform native to OpenTelemetry with traces and metrics. opensource.
Vector database plugin for Postgres, written in Rust, specifically designed for LLM.
Open-source vector similarity search for Postgres.
OpenAI-compatible LLM inference server for Apple Silicon using MLX. 2-4x faster than Ollama with tool calling and prompt caching.
Provides containers to encapsulate and deploy EdgeML pipelines and applications.
MLOps framework to package, deploy, monitor and manage thousands of production machine learning models.
Python-free Rust inference server with OpenAI API compatibility and hot model swapping.
An MLOps/LLMOps platform for model building, evaluation, and fine-tuning.