Struct GroupedGemmOptions 

pub struct GroupedGemmOptions {
    pub max_working_bytes: usize,
}

Resource limits for a shared-buffer grouped GEMM.

max_working_bytes bounds the temporary descriptor translation owned by the tensorbackend facade. It does not attempt to account for provider-owned internal workspace. The default is unlimited; callers with a strict memory contract should set an explicit limit and include the descriptor metadata in that budget.

Examples

use tensor4all_tensorbackend::GroupedGemmOptions;

let options = GroupedGemmOptions { max_working_bytes: 4096 };
assert_eq!(options.max_working_bytes, 4096);
assert_eq!(GroupedGemmOptions::default().max_working_bytes, usize::MAX);

Fields

max_working_bytes: usize

Maximum temporary bytes used to translate jobs for the provider.

Trait Implementations

impl Clone for GroupedGemmOptions

fn clone(&self) -> GroupedGemmOptions

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for GroupedGemmOptions

impl Debug for GroupedGemmOptions

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

Formats the value using the given formatter.

impl Default for GroupedGemmOptions

fn default() -> Self

Returns the “default value” for a type.

impl Eq for GroupedGemmOptions

impl PartialEq for GroupedGemmOptions

fn eq(&self, other: &GroupedGemmOptions) -> 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 StructuralPartialEq for GroupedGemmOptions