Causal, Higher-Order, Probabilistic Programming

[NeurIPS 2025] Encoder-Decoder Diffusion Language Models for Efficient Training and Inference

Accessible large language models via k-bit quantization for PyTorch.

LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

TL;DR: We only have one life. Let's stop wasting it on YouTube shorts.

Fast and memory-efficient exact attention

Minimal and annotated implementations of key ideas from modern deep learning research.

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

Debug PyTorch code using PySnooper

A comprehensive JAX/NNX library for diffusion and flow matching generative algorithms, featuring DiT (Diffusion Transformer) and its variants as the primary backbone with support for ImageNet train…

Serialize JAX, Flax, Haiku, or Objax model params with 🤗`safetensors`

📊 Save matplotlib figures as TikZ/PGFplots for smooth integration into LaTeX.

Official PyTorch implementation for ICLR2025 paper "Scaling up Masked Diffusion Models on Text"

Awesome Reasoning LLM Tutorial/Survey/Guide

Post-training with Tinker

Code for "Variational Reasoning for Language Models"

Muon is Scalable for LLM Training

Kimi K2 is the large language model series developed by Moonshot AI team

List of AI Internships

JAX implementation of MeanFlow

[ICML 2025] Customizing the Inductive Biases of Softmax Attention using Structured Matrices

EDM2 and Autoguidance -- Official PyTorch implementation

Supporting code for the blog post on modular manifolds.