Module tp 

K3 tensor-parallel storage plan, shared by host loading and device binding. Config head counts are rank-local; expert and dense widths remain full.

Structs

TpBytePlan

Byte ranges from one full checkpoint tensor that form this rank’s tensor. Ranges preserve row-major packed nibbles and their matching E8M0 groups.

Enums

TpAxis

Functions

plan_tensor_bytes

Plan checkpoint storage BEFORE allocating a device buffer.

tensor_plan