oa::matrix::moe_expert_plan
Build a stable dropless expert-major plan from I32 [T, K] indices. Within every expert, routes preserve their original token-major order. The operation accepts at most 256 experts, matching the shader’s shared state. Errors Returns an error unless indices are nonempty rank-two I32, the expert count is in 1..=256, sizes fit the admitted ABI, allocation succeeds, or runtime recording succeeds.
Function Documentation
Build a stable dropless expert-major plan from I32 [T, K] indices. Within every expert, routes preserve their original token-major order. The operation accepts at most 256 experts, matching the shader’s shared state. Errors Returns an error unless indices are nonempty rank-two I32, the expert count is in 1..=256, sizes fit the admitted ABI, allocation succeeds, or runtime recording succeeds.