For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).
Mojo struct
CumSum
struct CumSum
Registers the mo.cumsum graph op with the graph compiler.
Implemented traits
Methods
execute
static def execute[dtype: DType, rank: Int, exclusive: Int, reverse: Int, axis: Int](output: ManagedTensorSlice[IOSpec[_, _].Output, static_spec=output.static_spec], input: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=input.static_spec], ctx: DeviceContext)
Executes the mo.cumsum graph op.
Parameters:
- dtype (
DType): Element type of the input and output tensors. - rank (
Int): Tensor rank of the input and output tensors. - exclusive (
Int): See the graph op signature. - reverse (
Int): See the graph op signature. - axis (
Int): Dimension along which to reduce.
Args:
- output (
ManagedTensorSlice[IOSpec[_, _].Output, static_spec=output.static_spec]): Output tensor receiving the result. - input (
ManagedTensorSlice[IOSpec[_, _].Input, static_spec=input.static_spec]): Input tensor to reduce. - ctx (
DeviceContext): Device context used to enqueue the kernel.
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!