Word Embeddings: the full implementation of word2vec, GloVe in Go.
Directory
Search results
Published directory entries matching your search.
A Julia package for Princeton's WordNet.
An Autonomous LLM Agent for Complex Task Solving.
Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library.
Ultralytics' YOLOv8 implementation with C++ support for real-time object detection and tracking, optimized for edge devices.
Light-weight, universal resource scheduler for container orchestrator systems.
AI evaluation platform for interactively exploring data and model outputs.
Automatic "Differentiation" via Text, using large language models to backpropagate textual gradients.
Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.
Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.
Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.
Bayesian Inference Tools in Python.
An open-source LLM gateway with routing, load balancing, guardrails, and observability for 1000+ models. opensource.
Deploy a ML inference service on a budget in less than 10 lines of code.
Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.
An easy-to-use feature store. Optimized for time-series data.
Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.
Open-source tool that lets you package ML models in a standard, production-ready container.
Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.
Fast inference engine for Transformer models in C++.
Curated list of awesome vector search framework/engine, library, cloud service and research papers to vector similarity search.
Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
10x faster, cheaper, and better vector database.