cubek-attention
| Crates.io | cubek-attention |
| lib.rs | cubek-attention |
| version | 0.1.1 |
| created_at | 2025-12-05 17:13:38.608748+00 |
| updated_at | 2026-01-23 17:03:14.354469+00 |
| description | CubeK: Attention Kernels |
| homepage | |
| repository | https://github.com/tracel-ai/cubek/tree/main/crates/cubek-attention |
| max_upload_size | |
| id | 1968745 |
| size | 428,412 |
Nathaniel Simard (nathanielsimard)
documentation
README
CubeK: high-performance multi-platform kernels in CubeCL
Algorithms
| Algorithms | Variants |
|---|---|
| Random | bernoulli normal uniform |
| Quantization | symmetric per-block per-tensor q2 q4 q8 fp4 |
| Reduction | mean sum prod max min arg[max|min] per-cube per-plane |
| Matmul | mma unit tma multi-stage specialization ordered multi-rows |
| Convolution | mma unit tma multi-stage im2col |
| Attention | mma unit multi-rows |
Contributing
If you want to contribute new kernels, please read the GUIDE.md.