LLM Council works together to answer your hardest questions

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Open-source implementation of AlphaEvolve

Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

Blazingly fast LLM inference.

An introduction to LLM Sampling

Rust library for generating vector embeddings, reranking. Re-write of qdrant/fastembed.

Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.

This Python script scrapes information about AI models from the Ollama library website (https://ollama.com/library).

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

Solve puzzles. Learn CUDA.

Solve Puzzles. Learn Metal 🤘

Flutter database for super-fast Dart object persistence

Run PyTorch LLMs locally on servers, desktop and mobile

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance…

LLM training in simple, raw C/CUDA

The Modular Platform (includes MAX & Mojo)

📚 Personal collection of ChatGPT prompts for developers!

Spherical Merge Pytorch/HF format Language Models with minimal feature loss.

llama.cpp bindings for Flutter

Examples in the MLX framework

An Extensible Deep Learning Library

MLX: An array framework for Apple silicon