Built a tensor + NN framework entirely in Mojo — feedback?

Tenmo A lightweight tensor library and neural network framework written in pure Mojo.

https://github.com/ratulb/tenmo

Tenmo focuses on:

SIMD-optimization explicit memory layout zero-copy views a minimal but practical autograd system Status: Tenmo evolves alongside Mojo itself. APIs may change. Not production-ready yet.

Performance MNIST (4-layer MLP, 105K params, 15 epochs) Platform Device Avg Epoch Total Test Acc Tenmo CPU (Mojo) 11.4s 171s 97.44% PyTorch CPU 14.5s 218s 98.26% PyTorch GPU (Tesla T4) 15.2s 227s 97.87% Notes

Tenmo uses SIMD-vectorized kernels on contiguous buffers. No BLAS was used in the MNIST run — everything executes as pure Mojo code. GPU overhead dominates for models of this size; larger models benefit more from GPU acceleration. Quick Example from testing import assert_true from tenmo import Tensor

fn main() raises: var a = Tensor.d1([1.0, 2.0, 3.0], requires_grad=True)

    var b = a * 2
    var c = a * 3
    var d = b + c

    d.backward()

    assert_true(a.grad().all_close(Tensor.d1([5.0, 5.0, 5.0])))

Feedback highly appreciated!