Enum ExpertArm 

pub enum ExpertArm {
    Bf16Dequant,
    Native,
}

Lane 7: which expert-GEMM realization runs. Bf16Dequant = the lane-4 gated rung (on-the-fly exact dequant + cuBLASLt bf16, the fallback and A/B reference). Native = the reference-law quantized GEMMs (act_quant per-128 FP8 codes × as-stored NVFP4/MXFP4 slabs, kernel.py fp4_gemm arithmetic — RECEIPTS.md “Lane 7”). Selected by MEMRA_DSV4_EXPERT_ARM=native via [memra_gguf::dsv4_forward:: expert_arm_native] — the SAME seam the CPU oracle reads, so one invocation can never mix numeric classes.

Variants

Bf16Dequant

Native

Trait Implementations

impl Clone for ExpertArm

fn clone(&self) -> ExpertArm

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Copy for ExpertArm

impl Debug for ExpertArm

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Eq for ExpertArm

impl PartialEq for ExpertArm

fn eq(&self, other: &ExpertArm) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl StructuralPartialEq for ExpertArm