slime is an LLM post-training framework for RL Scaling.

Library for reading and processing ML training data.

FlashInfer: Kernel Library for LLM Serving

Fully open reproduction of DeepSeek-R1

A sparse attention kernel supporting mix sparse patterns

Efficient Triton Kernels for LLM Training

Everything about the SmolLM and SmolVLM family of models

HunyuanVideo: A Systematic Framework For Large Video Generation Model

A bibliography and survey of the papers surrounding o1

All Algorithms implemented in Python

jax-triton contains integrations between JAX and OpenAI Triton

A PyTorch native platform for training generative AI models

A beautiful, simple, clean, and responsive Jekyll theme for academics

MiniCPM-o 4.5: A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Mulitmodal Live Streaminig on Your Phone

DSPy: The framework for programming—not prompting—language models

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

[CVPR'23] Video Probabilistic Diffusion Models in Projected Latent Space

[CVPR 2022] StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2

Let us control diffusion models!

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Open-Sora: Democratizing Efficient Video Production for All

[CSUR] A Survey on Video Diffusion Models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Tile primitives for speedy kernels

RWKV model implementation

Triton-based implementation of Sparse Mixture of Experts.