mattn / tensai

What it does

• Matrix operations. Matrix plus basic operations such as Dot, Add, T, and AddBias. Tensors are float32 (tensai.Float)
• N-dimensional tensors. Tensor generalizes Matrix to any rank: element-wise Add/Sub/Mul/Div with NumPy-style broadcasting, batched MatMul (the leading axes broadcast, the per-matrix products run on the same kernel as Dot, parallelized acros
• SIMD acceleration. AVX2 kernels on amd64 and NEON (ARM's Advanced SIMD) kernels on arm64, written with Go's experimental simd/archsimd package: still pure Go, no cgo, no assembly files. Matmul, ReLU/LeakyReLU, Sigmoid/Tanh/Softmax (via a v
• Low-allocation training. layers reuse their forward/backward scratch buffers across training steps (a full MLP step runs in ~29 allocations), so GC stays out of the training loop; Predict always returns freshly allocated results
• Layers. Embedding, Dense, Conv2D, MaxPool2D, BatchNorm, LayerNorm, Dropout, plus ReLU, LeakyReLU, GELU, Sigmoid, Tanh, and Softmax activations