mirror of
https://github.com/tinygrad/tinygrad.git
synced 2026-02-19 02:44:40 -05:00
90fff82c8a
* assembler maybe * custom asm * rdna3 on quiet * trigger crashes * fixed notes * non-fatal rdna2 crash * Crash4 * improve rdna sniffer * comments * improve sniffer * asm * 131 TFLOPS RDNA3 * opt simple matmul * todos
6 lines
213 B
Python
6 lines
213 B
Python
from tinygrad.tensor import Tensor
|
|
N = 1024
|
|
a, b = Tensor.randn(N, N), Tensor.randn(N, N)
|
|
c = (a.reshape(N, 1, N) * b.permute(1,0).reshape(1, N, N)).sum(axis=2)
|
|
print((c.numpy() - (a.numpy() @ b.numpy())).mean())
|