For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).
Mojo function
placement
def placement[L: TensorLayout]() -> BitLayout
Returns a static layout as a BitLayout from coordinate bits to offset bits.
Coordinate bits number the layout's points colexicographically: mode 0's
bits are the lowest. Bit b of mode i goes to stride_i << b, or
nowhere for a stride of zero.
Parameters:
- L (
TensorLayout): The layout, whichis_bit_linear.
Returns:
BitLayout: The layout's placement.