Struct ExpertRecordSpec 

pub struct ExpertRecordSpec {
    pub inter: u64,
    pub hidden: u64,
    pub group_size: u64,
    pub sub_align: u64,
    /* private fields */
}

Where every sub-buffer of one expert record sits, relative to the record’s base. Shared by the offline builder (to place bytes) and the streamer (to compute the device pointers it patches into the ExpertPtrTable).

Layout within a record (all offsets are relative to the record base and are aligned to sub_align, which must satisfy the fused MoE kernels’ pointer alignment requirement):

  [ header (ExpertRecordHeader::BYTES) ]
  [ gate.packed ][ gate.scale ]
  [ up.packed   ][ up.scale   ]
  [ down.packed ][ down.scale ]
  [ pad to record_stride ]

Fields

inter: u64

hidden: u64

group_size: u64

sub_align: u64

Implementations

impl ExpertRecordSpec

pub fn new(inter: u64, hidden: u64, group_size: u64, sub_align: u64) -> Self

Build the canonical record layout for a model whose experts have the given inter(mediate) and hidden dims. sub_align is the alignment applied to every sub-buffer (256 is a safe default for CUTLASS/MMQ).

pub fn proj_bytes(&self, p: Proj) -> ProjBytes

pub fn packed_off(&self, p: Proj) -> u64

Offset of a projection’s packed-weight sub-buffer within the record.

pub fn scale_off(&self, p: Proj) -> u64

Offset of a projection’s block-scale sub-buffer within the record.

pub fn raw_bytes(&self) -> u64

Total raw record bytes (header + sub-buffers), before I/O-block rounding.

pub fn payload_bytes(&self) -> u64

Sum of all six sub-buffer payloads (excludes header + alignment padding).

Trait Implementations

impl Clone for ExpertRecordSpec

fn clone(&self) -> ExpertRecordSpec

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ExpertRecordSpec

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

Formats the value using the given formatter.

impl PartialEq for ExpertRecordSpec

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

Tests for self and other values to be equal, and is used by ==.

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

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Copy for ExpertRecordSpec

impl Eq for ExpertRecordSpec

impl StructuralPartialEq for ExpertRecordSpec