diff --git a/docs/lang/articles/get-started/accelerate_pytorch.md b/docs/lang/articles/get-started/accelerate_pytorch.md index 4527bf1b6ce94..c30efa7fd82e5 100644 --- a/docs/lang/articles/get-started/accelerate_pytorch.md +++ b/docs/lang/articles/get-started/accelerate_pytorch.md @@ -180,9 +180,9 @@ The Taichi reference code is almost identical to its Python counterpart. And a g ```python @ti.kernel def taichi_forward_v0( - out: ti.types.ndarray(field_dim=3), - w: ti.types.ndarray(field_dim=3), - k: ti.types.ndarray(field_dim=3), + out: ti.types.ndarray(ndim=3), + w: ti.types.ndarray(ndim=3), + k: ti.types.ndarray(ndim=3), eps: ti.f32): for b, c, t in out: