Fully automatic censorship removal for language models

The Deno Sandbox Python SDK

python-based eDSL for efficient Metal Shading Language code generation

Minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models.

A lightweight inference engine supporting speculative speculative decoding (SSD).

Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

Training neural networks on Apple Neural Engine via reverse-engineered private APIs

A minimal PyTorch re-implementation of Qwen 3.5

Code for "EgoX: Egocentric Video Generation from a Single Exocentric Video"

GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 training.

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

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

TheBoringNotch: Not so boring notch That Rocks 🎸🎶

Anthropic's original performance take-home, now open for you to try!

Fetch source code for npm packages to give AI coding agents deeper context

Browser automation CLI for AI agents

Minimal Claude Code alternative. Single Python file, zero dependencies, ~250 lines.

~950 line, minimal, extensible LLM inference engine built from scratch.

MoE training for Me and You and maybe other people

My learning notes for ML SYS.

Kernels, of the mega variety :)

A framework for the evaluation of autoregressive code generation language models.

Code for the paper "Efficient Training of Language Models to Fill in the Middle"

Code for the paper "Evaluating Large Language Models Trained on Code"

This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

NanoGPT (124M) in 2 minutes

Official repository for LiteTracker: Leveraging Temporal Causality for Accurate Low-latency Tissue Tracking; published at MICCAI 2025.

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling