sandyresearch/chipmunk

🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× vs cuBLAS

30
/ 100
Emerging

This project dramatically speeds up the creation of AI-generated images and videos, helping you produce visual content much faster. It takes your existing diffusion model (like HunyuanVideo or FLUX.1-dev) and processes it more efficiently. Creative professionals, content creators, or researchers working with generative AI will find this invaluable for accelerating their workflows.

101 stars. No commits in the last 6 months.

Use this if you are generating images or videos with diffusion models on NVIDIA H100 GPUs and want to significantly reduce the time it takes to produce your output.

Not ideal if you are not using diffusion transformer models or if your primary bottleneck is not related to attention or MLP layers during generation.

AI-art video-production generative-AI content-creation AI-research
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 15 / 25
Community 4 / 25

How are scores calculated?

Stars

101

Forks

2

Language

Cuda

License

MIT

Last pushed

Sep 08, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sandyresearch/chipmunk"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.