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

broadcast

Multi-GPU broadcast kernel implementation.

Functions

• ​broadcast: Broadcast data from root GPU to all participating GPUs.
• ​broadcast_2stage: Two-stage broadcast: scatter from root, then allgather among all GPUs.
• ​broadcast_multimem_kernel: Broadcast kernel using multimem.st for multicast writes.
• ​broadcast_pull_1stage_kernel: Single-stage pull broadcast kernel: each GPU reads root's input directly.
• ​broadcast_pull_2stage_kernel: Two-stage broadcast: scatter from root, then allgather among all GPUs.