High-Resolution Image Synthesis with Latent Diffusion Models

A high-throughput and memory-efficient inference and serving engine for LLMs

Deep learning framework to train, deploy, and ship AI products Lightning fast.

The official implementation of "LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception"

Simple RL training for reasoning

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

Code/data for MARG (multi-agent review generation)

httpx is a fast and multi-purpose HTTP toolkit that allows running multiple probes using the retryablehttp library.

Uniform Manifold Approximation and Projection

Run a conference from your backyard.

Benchmarking LLMs with Challenging Tasks from Real Users

Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

A Dynamic Benchmark for Evaluating LLMs in the Wild

The official Python library for the OpenAI API