tools · nvidia
CUDA C++ template library of high-performance GEMM and attention primitives. Basis for many fused kernels.
| Weight file SHA-256 | 81c14b56ba6caf6bfee78a15dad5143cbe64748cbb3d355bf07452d5789c98a0 |
|---|
| Publisher | nvidia |
|---|---|
| Origin | United States |
| Licence | BSD-3 |
| Pulls recorded here | 240,001 |
Registry record as of 2026-06-06. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.