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 module
concat
Implements tensor concatenation along a specified axis for CPU and GPU targets.
comptime values
ElementwiseEpilogueFn
comptime ElementwiseEpilogueFn = def[c_type: DType, width: SIMDLength, *, alignment: Int](Coord[*?], SIMD[c_type, width]) -> None & RegisterPassable & ImplicitlyCopyable
Fused concat output epilogue: (coord, value) -> None.
A unified closure passed as a runtime value carries the origins of its
captures, so the output it writes stays alive until the kernel that calls it
has launched. width and alignment have no defaults.
Functions
-
concat: Concatenatesinputsalongaxisintooutputfor the giventarget. -
concat_shape: Compute the output shape of apadoperation, and assert the inputs are compatible. -
fused_concat: Concatenates inputs produced byinput_fnalongaxis, handing each element tooutput_0_fn. -
memcpy_or_fuse: Copiesnbytes fromsrc_dataintodest_dataatout_byte_offset, applyingepilogue_fnelementwise whenhas_epilogueis set. -
preferred_simd_width: SIMD scalar count for fused GPU concat vectorization.