Stars
nw_wrld is an event-driven sequencer for triggering visuals using web technologies. It enables users to scale up audiovisual compositions for prototyping, demos, exhibitions, and live performances.…
Agentic Design Patterns: A Hands-On Guide to Building Intelligent Systems by Antonio Gulli
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Slide decks, coding exercises, and quick references for learning the JAX AI Stack
Unified benchmark for evaluating conversational memory and RAG across multiple datasets
SGLang is a high-performance serving framework for large language models and multimodal models.
A gradient stability controller for neural network training. It suppresses divergence under extreme learning rates, mitigates shock events, and enables fast recovery from catastrophic or noisy batc…
Adaptive Single/Multi/Mirror LoRA framework with automatic mode switching driven by synaptic stress signal φ(t). Validated on Llama-3.2-1B (Tinker) and GLUE MRPC with full stress-recovery cycle dem…
a simple c++ inference engine for gpt based architecture
Open standard for machine learning interoperability
The Qubic Core is the Node Software which runs the Qubic Network
Repo for AI Compiler team. The intended purpose of this repo is for implementation of a PJRT device.
🤘 TT-NN operator library, and TT-Metalium low level kernel programming model.
An open-source AI agent that brings the power of Gemini directly into your terminal.
Post-training with Tinker
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
An interface library for RL post training with environments.
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
Janus-Series: Unified Multimodal Understanding and Generation Models
The simplest, fastest repository for training/finetuning small-sized VLMs.