A Claude Code skill that turns any codebase into a beautiful, interactive single-page HTML course for non-technical vibe coders.

Tutorials for Triton, a language for writing gpu kernels

SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention

Kandinsky 5.0: A family of diffusion models for Video & Image generation

[ICLR 2026] LongLive: Real-time Interactive Long Video Generation

HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

[NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning

Wan: Open and Advanced Large-Scale Video Generative Models

[ICML 2025] The Diffusion Duality

Supercharge Your LLM with the Fastest KV Cache Layer

TinyChatEngine: On-Device LLM Inference Library

KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)

I seek to draw from the philosophies embedded in AI research to inspire deeper reflection on life — exploring how the principles that guide intelligent systems can illuminate the way we live, think…

EB1A DIY Collection

[ICCV 2025 (Highlight)] DIMO: Diverse 3D Motion Generation for Arbitrary Objects

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

Kernels, of the mega variety :)

A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and caching, etc.

Fast and memory-efficient exact attention

Efficient Triton Kernels for LLM Training

[ICCV 2025] GameFactory: Creating New Games with Generative Interactive Videos

(CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

MAGI-1: Autoregressive Video Generation at Scale

Open-source unified multimodal model

Lets make video diffusion practical!

CUDA integration for Python, plus shiny features

Material for gpu-mode lectures

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

Interactive visualizations of the geometric intuition behind diffusion models.