A full-stack LLM development toolkit from NVIDIA covering synthetic data generation, multi-backend inference, model training, and 11-category benchmark evaluation, scaling from single GPU to tens-of-thousands-GPU Slurm clusters.
An RL training environment building library for LLMs, providing complete infrastructure from development and testing to scaled rollout collection, with built-in RLVR scenarios and tool-calling support.
The Open Source AI Engineering Platform for Agents, LLMs & Models, providing experiment tracking, model registry, LLM observability, evaluation, prompt optimization, and a unified AI gateway.
A Rust-based cross-platform CLI tool that right-sizes LLM models to your system's RAM, CPU, and GPU by detecting specs and recommending optimal models and quantization strategies. Covers 206 models from 57 providers.
A minimal, hackable experimental harness for training LLMs on a single GPU node, covering all stages from pretraining to a ChatGPT-like UI.
An open-source framework by Stream for building vision AI agents that work with any model or video provider, leveraging Stream's edge network for ultra-low latency video experiences.
AirLLM optimizes inference memory usage, enabling 70B large language models to run on a single 4GB GPU card without quantization, distillation, or pruning. It now also supports running 405B Llama3.1 models on 8GB VRAM.
A modern AI gateway system that provides a unified OpenAI, Anthropic, Gemini and AI SDK compatible API, enabling seamless integration across multiple AI providers with automatic request translation and comprehensive tracing capabilities.
Microsoft's family of open-source frontier voice AI models including both Text-to-Speech (TTS) and Automatic Speech Recognition (ASR) models, designed for long-form audio processing with multilingual support.
Trinity-RFT is a general-purpose, flexible and user-friendly framework for LLM reinforcement fine-tuning (RFT). It decouples RFT into three coordinated components: Explorer, Trainer, and Buffer, enabling users with different backgrounds to train LLM-powered agents for specific domains.
Page 1 / 3 · 22 total
Get the latest AI tools and trends delivered straight to your inbox. No spam, just intelligence.
