One-time purchase — yours forever
One-time payment via Stripe. Includes all current wheels for every supported GPU.
Stay current as Colab updates
Billed monthly by Stripe. We never see your card. Cancel or manage anytime.
If you just need the current set of wheels and don't care about future updates, the Colab Survival Pack is the best value — one payment and you're set. If you want to stay current every time Google updates the Colab runtime or when new package versions drop, the Pro Subscription keeps you covered automatically.
Buy individual packages if you only need a specific wheel.
More individual wheels coming soon. Need a specific one? Support
Both plans include every wheel below, prebuilt and guaranteed to work against CUDA 12.8, PyTorch 2.10, and Python 3.12 on Google Colab. Every wheel installs cleanly alongside the default Colab stack — no uninstalls, no version conflicts, no battling dependencies.
Flash Attention 2 — efficient transformer inference on A100/L4/T4.
Memory-efficient attention and transformer building blocks from Meta.
NVIDIA's differentiable rasterizer for 3D deep learning.
CUDA-accelerated mesh processing for 3D pipelines.
Flexible GEMM kernels for mixed-precision on Ampere GPUs.
CUDA voxel utilities for 3D pipeline work.
Neural rendering components for reconstruction pipelines.
3D math and geometry with CUDA acceleration.
Run GGUF-quantized Stable Diffusion models. Compiled for frictionless T4 compatibility.
| Spec | Details |
|---|---|
| GPU | NVIDIA A100 NVIDIA L4 NVIDIA T4 |
| Platform | Google Colab linux x86_64 |
| Python | 3.12 |
| CUDA | 12.8 |
| PyTorch | 2.10 |