RealmOA Library

oa::ml::matrix::grouped_linear_m

Apply one affine projection per expert to expert-major packed rows. input is F32 [R, K], weight is F32 [E, N, K], bias is F32 [E, N], and offsets is the U32 [E+1] boundary output from crate::matrix::moe_expert_plan. The result is F32 [R, N]. Errors Returns an error for incompatible shapes, dtypes, engine ownership, shader ABI overflow, allocation failure, or runtime recording failure.

FnRust public API

Function Documentation

pub fn grouped_linear_m( input: &Matrix, weight: &Matrix, bias: &Matrix, offsets: &Matrix ) -> Result<Matrix>
Apply one affine projection per expert to expert-major packed rows. input is F32 [R, K], weight is F32 [E, N, K], bias is F32 [E, N], and offsets is the U32 [E+1] boundary output from crate::matrix::moe_expert_plan. The result is F32 [R, N]. Errors Returns an error for incompatible shapes, dtypes, engine ownership, shader ABI overflow, allocation failure, or runtime recording failure.