# Tensors & Kernels

Neutron for Mojo provides type-safe tensors with compile-time dimension checking, backed by SIMD-accelerated kernels on the hot path. See the [overview](/docs/mojo/overview) for the project's preview status.

## Tensor Operations

```mojo
from neutron.tensor import Tensor, Dim, matmul, softmax, rmsnorm

# Typed dimensions (compile-time shape safety)
alias Batch = Dim[0]
alias Seq = Dim[1]
alias Hidden = Dim[2]

# Core operations
let output = matmul(weights, input)      # Matrix multiply
let probs = softmax(logits, axis=-1)     # Softmax
let normed = rmsnorm(x, weight, 1e-5)    # RMS normalization
let activated = silu(x)                   # SiLU activation
```

## SIMD Kernels

Hot-path operations use SIMD intrinsics for maximum throughput:

| Function | Description |
|----------|-------------|
| `simd_dot(a, b)` | Dot product |
| `simd_matvec(A, v)` | Matrix-vector multiply |
| `simd_rmsnorm(x, w, eps)` | RMS layer normalization |
| `simd_attention_scores(Q, K, scale)` | Attention score computation |
| `simd_online_softmax_attention(Q, K, V)` | Fused attention (FlashAttention-style) |

## Additional Operations

```mojo
layernorm(x, weight, bias)    # Layer normalization
gelu(x)                       # GELU activation
swiglu(x, w1, w2, w3)        # SwiGLU (used in LLaMA)
```