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
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.
Stars
101
Forks
2
Language
Cuda
License
MIT
Category
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.
Higher-rated alternatives
openvinotoolkit/nncf
Neural Network Compression Framework for enhanced OpenVINO™ inference
huggingface/optimum
🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers...
NVIDIA/Megatron-LM
Ongoing research training transformer models at scale
huggingface/optimum-intel
🤗 Optimum Intel: Accelerate inference with Intel optimization tools
eole-nlp/eole
Open language modeling toolkit based on PyTorch